Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.3198. Min Act: -0.1700
Data Index: 1914649 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.3198. Min Act: -0.1700
Data Index: 3066194 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.1323. Min Act: -0.1700
Data Index: 2175954 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.1323. Min Act: -0.1700
Data Index: 6840712 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3198. Min Range: -8.3198
Max Act: 8.0073. Min Act: -0.1700
Data Index: 5400438 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.7260. Min Act: -0.1700
Data Index: 5940737 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6635. Min Act: -0.1700
Data Index: 4858183 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6635. Min Act: -0.1700
Data Index: 4666346 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.6010. Min Act: -0.1700
Data Index: 1718300 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5698. Min Act: -0.1700
Data Index: 8749437 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5698. Min Act: -0.1700
Data Index: 7341559 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5385. Min Act: -0.1700
Data Index: 688283 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5385. Min Act: -0.1700
Data Index: 1002385 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5073. Min Act: -0.1700
Data Index: 3240668 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5073. Min Act: -0.1700
Data Index: 7836 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.5073. Min Act: -0.1700
Data Index: 6069180 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.4760. Min Act: -0.1700
Data Index: 3356056 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.4448. Min Act: -0.1700
Data Index: 426533 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.4448. Min Act: -0.1700
Data Index: 4319408 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3198. Min Range: -8.3198
Max Act: 7.4448. Min Act: -0.1700
Data Index: 8501850 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19