Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.9997. Min Act: -0.1700
Data Index: 3074235 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.8122. Min Act: -0.1700
Data Index: 4809262 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.6247. Min Act: -0.1700
Data Index: 534156 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.5935. Min Act: -0.1700
Data Index: 2905930 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.5622. Min Act: -0.1700
Data Index: 3049432 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.5622. Min Act: -0.1700
Data Index: 3271984 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.5310. Min Act: -0.1700
Data Index: 1812584 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 815385 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 7643372 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4997. Min Act: -0.1700
Data Index: 8749240 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4685. Min Act: -0.1700
Data Index: 7860263 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4685. Min Act: -0.1700
Data Index: 2056232 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4685. Min Act: -0.1700
Data Index: 467384 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6736735 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4685. Min Act: -0.1700
Data Index: 660428 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6349168 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4372. Min Act: -0.1700
Data Index: 819499 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4372. Min Act: -0.1700
Data Index: 8445212 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4060. Min Act: -0.1700
Data Index: 4175365 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9997. Min Range: -5.9997
Max Act: 5.4060. Min Act: -0.1700
Data Index: 220139 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19