Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1500 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.3060. Min Act: -0.1700
Data Index: 4326485 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.1488. Min Act: -0.1700
Data Index: 1641109 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.1330. Min Act: -0.1700
Data Index: 6664508 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.1015. Min Act: -0.1700
Data Index: 6664509 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.1015. Min Act: -0.1700
Data Index: 5027151 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0858. Min Act: -0.1700
Data Index: 8738726 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0700. Min Act: -0.1700
Data Index: 4979233 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0227. Min Act: -0.1700
Data Index: 6100514 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0384. Min Act: -0.1700
Data Index: 6903602 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0227. Min Act: -0.1700
Data Index: 4879601 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0227. Min Act: -0.1700
Data Index: 8445978 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0227. Min Act: -0.1700
Data Index: 890096 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0069. Min Act: -0.1700
Data Index: 4389542 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0069. Min Act: -0.1700
Data Index: 6721847 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0069. Min Act: -0.1700
Data Index: 5039721 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3060. Min Range: -3.3060
Max Act: 2.9911. Min Act: -0.1700
Data Index: 4028134 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3060. Min Range: -3.3060
Max Act: 3.0069. Min Act: -0.1700
Data Index: 7233496 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3060. Min Range: -3.3060
Max Act: 2.9911. Min Act: -0.1700
Data Index: 6005739 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3060. Min Range: -3.3060
Max Act: 2.9911. Min Act: -0.1700
Data Index: 7556190 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3060. Min Range: -3.3060
Max Act: 2.9752. Min Act: -0.1700
Data Index: 3562502 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19