Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0086. Min Range: -4.0086
Max Act: 4.0086. Min Act: -0.1700
Data Index: 1874984 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.9461. Min Act: -0.1700
Data Index: 4570268 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.9461. Min Act: -0.1700
Data Index: 1903018 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.9148. Min Act: -0.1700
Data Index: 4881610 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.9148. Min Act: -0.1700
Data Index: 3170244 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8835. Min Act: -0.1700
Data Index: 8238745 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8835. Min Act: -0.1700
Data Index: 4570264 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8835. Min Act: -0.1700
Data Index: 1649134 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8835. Min Act: -0.1700
Data Index: 6389560 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8523. Min Act: -0.1700
Data Index: 7251493 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8523. Min Act: -0.1700
Data Index: 7822729 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8523. Min Act: -0.1700
Data Index: 7081048 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8523. Min Act: -0.1700
Data Index: 7890791 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8210. Min Act: -0.1700
Data Index: 6540510 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8523. Min Act: -0.1700
Data Index: 3981722 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.8210. Min Act: -0.1700
Data Index: 8765894 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.7897. Min Act: -0.1700
Data Index: 925937 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.7897. Min Act: -0.1700
Data Index: 2433211 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.7897. Min Act: -0.1700
Data Index: 5330941 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0086. Min Range: -4.0086
Max Act: 3.7897. Min Act: -0.1700
Data Index: 5582632 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19