Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0898. Min Range: -6.0898
Max Act: 6.0898. Min Act: -0.1700
Data Index: 1696250 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0898. Min Range: -6.0898
Max Act: 6.0585. Min Act: -0.1700
Data Index: 2775638 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0898. Min Range: -6.0898
Max Act: 6.0585. Min Act: -0.1700
Data Index: 1589099 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.9335. Min Act: -0.1700
Data Index: 4666346 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.9023. Min Act: -0.1700
Data Index: 2899704 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.9023. Min Act: -0.1700
Data Index: 1867594 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.8398. Min Act: -0.1700
Data Index: 249423 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.7773. Min Act: -0.1700
Data Index: 4952797 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.7460. Min Act: -0.1700
Data Index: 8054831 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.7460. Min Act: -0.1700
Data Index: 5954382 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.7148. Min Act: -0.1700
Data Index: 1143867 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.7148. Min Act: -0.1700
Data Index: 3424651 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.7148. Min Act: -0.1700
Data Index: 1315016 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6835. Min Act: -0.1700
Data Index: 3911503 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6835. Min Act: -0.1700
Data Index: 1589100 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6523. Min Act: -0.1700
Data Index: 5496810 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6835. Min Act: -0.1700
Data Index: 3826257 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6523. Min Act: -0.1700
Data Index: 7310441 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6835. Min Act: -0.1700
Data Index: 6848973 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0898. Min Range: -6.0898
Max Act: 5.6523. Min Act: -0.1700
Data Index: 3153570 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19