Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 268 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.1493. Min Act: -0.1700
Data Index: 6758720 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.1180. Min Act: -0.1700
Data Index: 589509 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.1180. Min Act: -0.1700
Data Index: 2331699 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.1493. Min Act: -0.1700
Data Index: 1960009 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.0868. Min Act: -0.1700
Data Index: 3115092 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.0555. Min Act: -0.1700
Data Index: 633872 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1493. Min Range: -7.1493
Max Act: 7.0243. Min Act: -0.1700
Data Index: 4747090 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.9930. Min Act: -0.1700
Data Index: 206406 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.9930. Min Act: -0.1700
Data Index: 5213281 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.9618. Min Act: -0.1700
Data Index: 6942576 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.9305. Min Act: -0.1700
Data Index: 7138010 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.9305. Min Act: -0.1700
Data Index: 6772119 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.8993. Min Act: -0.1700
Data Index: 1945774 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.8368. Min Act: -0.1700
Data Index: 2565182 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1640269 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.8680. Min Act: -0.1700
Data Index: 7983976 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.8055. Min Act: -0.1700
Data Index: 4743056 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.8055. Min Act: -0.1700
Data Index: 1764925 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.7743. Min Act: -0.1700
Data Index: 6672495 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1493. Min Range: -7.1493
Max Act: 6.7743. Min Act: -0.1700
Data Index: 1666947 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19