Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.6879. Min Act: -0.1700
Data Index: 7371876 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.6097. Min Act: -0.1700
Data Index: 6008343 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.5627. Min Act: -0.1700
Data Index: 5942461 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.5314. Min Act: -0.1700
Data Index: 7393917 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.5157. Min Act: -0.1700
Data Index: 8256268 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.5001. Min Act: -0.1700
Data Index: 2951459 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.5001. Min Act: -0.1700
Data Index: 2078959 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.5001. Min Act: -0.1700
Data Index: 7247971 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4687. Min Act: -0.1700
Data Index: 2905971 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4844. Min Act: -0.1700
Data Index: 7532152 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4687. Min Act: -0.1700
Data Index: 8177753 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4531. Min Act: -0.1700
Data Index: 1519938 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4531. Min Act: -0.1700
Data Index: 3337422 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4687. Min Act: -0.1700
Data Index: 8693086 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4374. Min Act: -0.1700
Data Index: 4082959 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4687. Min Act: -0.1700
Data Index: 2099518 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4374. Min Act: -0.1700
Data Index: 1796331 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4374. Min Act: -0.1700
Data Index: 1004108 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4061. Min Act: -0.1700
Data Index: 6897593 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6879. Min Range: -3.6879
Max Act: 3.4217. Min Act: -0.1700
Data Index: 140285 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19