Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3125. Min Range: -7.3125
Max Act: 7.3125. Min Act: -0.1700
Data Index: 5795033 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.8438. Min Act: -0.1700
Data Index: 6025439 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.8125. Min Act: -0.1700
Data Index: 491230 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.7813. Min Act: -0.1700
Data Index: 1329438 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.7188. Min Act: -0.1700
Data Index: 7283983 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.6250. Min Act: -0.1700
Data Index: 1518603 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5938. Min Act: -0.1700
Data Index: 5474402 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.6250. Min Act: -0.1700
Data Index: 6903125 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5938. Min Act: -0.1700
Data Index: 1826427 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5938. Min Act: -0.1700
Data Index: 6992925 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 5298722 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5313. Min Act: -0.1700
Data Index: 5490180 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5313. Min Act: -0.1700
Data Index: 7355269 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 6173821 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.4688. Min Act: -0.1700
Data Index: 8510854 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 1602284 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 1286904 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.4688. Min Act: -0.1700
Data Index: 8165499 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.4688. Min Act: -0.1700
Data Index: 3315788 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3125. Min Range: -7.3125
Max Act: 6.4688. Min Act: -0.1700
Data Index: 6513320 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19