Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4672527 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.4214. Min Act: -0.1700
Data Index: 1111192 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.2339. Min Act: -0.1700
Data Index: 2260055 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.2339. Min Act: -0.1700
Data Index: 1979346 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1402. Min Act: -0.1700
Data Index: 1169439 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1714. Min Act: -0.1700
Data Index: 1087656 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1714. Min Act: -0.1700
Data Index: 5491142 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1402. Min Act: -0.1700
Data Index: 2743923 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1089. Min Act: -0.1700
Data Index: 5578230 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1089. Min Act: -0.1700
Data Index: 7783057 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.1089. Min Act: -0.1700
Data Index: 4974729 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0777. Min Act: -0.1700
Data Index: 1062033 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0464. Min Act: -0.1700
Data Index: 3203799 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0777. Min Act: -0.1700
Data Index: 4264371 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0777. Min Act: -0.1700
Data Index: 6214522 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0464. Min Act: -0.1700
Data Index: 1476481 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0464. Min Act: -0.1700
Data Index: 2116290 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0777. Min Act: -0.1700
Data Index: 5184214 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5878491 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5152. Min Range: -5.5152
Max Act: 5.0464. Min Act: -0.1700
Data Index: 3108587 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19