Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 14.7949. Min Range: -14.7949
Max Act: 14.7949. Min Act: -0.1700
Data Index: 5214652 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.7949. Min Range: -14.7949
Max Act: 14.4199. Min Act: -0.1700
Data Index: 3460808 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.9824. Min Act: -0.1700
Data Index: 136267 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.8574. Min Act: -0.1697
Data Index: 5205764 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.9199. Min Act: -0.1700
Data Index: 3818896 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.6699. Min Act: -0.1700
Data Index: 5003672 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.7324. Min Act: -0.1700
Data Index: 1609864 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.6074. Min Act: -0.1700
Data Index: 6916249 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.6074. Min Act: -0.1700
Data Index: 5238269 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.6074. Min Act: -0.1700
Data Index: 389504 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.5449. Min Act: -0.1700
Data Index: 6684004 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.4824. Min Act: -0.1700
Data Index: 133055 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.4199. Min Act: -0.1700
Data Index: 2402631 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.4199. Min Act: -0.1700
Data Index: 2767657 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.4199. Min Act: -0.1700
Data Index: 4376363 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.3574. Min Act: -0.1700
Data Index: 6401344 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.3574. Min Act: -0.1700
Data Index: 2183037 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.4199. Min Act: -0.1700
Data Index: 1789521 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.2949. Min Act: -0.1700
Data Index: 6311544 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.7949. Min Range: -14.7949
Max Act: 13.2949. Min Act: -0.1700
Data Index: 1715197 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19