Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.7852. Min Act: -0.1700
Data Index: 6512214 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.6914. Min Act: -0.1700
Data Index: 3648654 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.6602. Min Act: -0.1700
Data Index: 8665978 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.6289. Min Act: -0.1700
Data Index: 6263167 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.6289. Min Act: -0.1700
Data Index: 7489791 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.6289. Min Act: -0.1700
Data Index: 2483515 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.6289. Min Act: -0.1700
Data Index: 6735182 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5977. Min Act: -0.1700
Data Index: 3103637 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5664. Min Act: -0.1700
Data Index: 8351128 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5352. Min Act: -0.1700
Data Index: 7466635 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5352. Min Act: -0.1700
Data Index: 7105171 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5352. Min Act: -0.1700
Data Index: 2998421 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5352. Min Act: -0.1700
Data Index: 5816924 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5352. Min Act: -0.1700
Data Index: 2863231 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5352. Min Act: -0.1700
Data Index: 4224930 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5039. Min Act: -0.1700
Data Index: 6243493 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5039. Min Act: -0.1700
Data Index: 5856846 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5039. Min Act: -0.1700
Data Index: 6290021 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5039. Min Act: -0.1700
Data Index: 4752755 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7852. Min Range: -5.7852
Max Act: 5.5039. Min Act: -0.1700
Data Index: 8455492 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19