Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5768 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.9103. Min Act: -0.1700
Data Index: 1470553 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.5978. Min Act: -0.1700
Data Index: 3087707 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.5041. Min Act: -0.1700
Data Index: 4991294 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3791. Min Act: -0.1700
Data Index: 6810026 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3478. Min Act: -0.1700
Data Index: 5239743 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3478. Min Act: -0.1700
Data Index: 6157313 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3166. Min Act: -0.1700
Data Index: 7311464 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3166. Min Act: -0.1700
Data Index: 1624959 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3166. Min Act: -0.1700
Data Index: 7402370 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.3166. Min Act: -0.1700
Data Index: 3342532 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2853. Min Act: -0.1700
Data Index: 2231223 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2853. Min Act: -0.1700
Data Index: 1716499 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 1924941 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 2443971 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 3381625 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 2137594 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6219093 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.1916. Min Act: -0.1700
Data Index: 717421 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 3119151 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9103. Min Range: -5.9103
Max Act: 5.2228. Min Act: -0.1700
Data Index: 6011556 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19