Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.8964. Min Act: -0.1700
Data Index: 217951 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.6777. Min Act: -0.1700
Data Index: 6772394 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.5527. Min Act: -0.1700
Data Index: 4696372 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.3027. Min Act: -0.1700
Data Index: 7336077 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.1777. Min Act: -0.1700
Data Index: 267759 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.1464. Min Act: -0.1700
Data Index: 1952641 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.1152. Min Act: -0.1700
Data Index: 2179441 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.1152. Min Act: -0.1700
Data Index: 369265 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8964. Min Range: -7.8964
Max Act: 7.0214. Min Act: -0.1700
Data Index: 54717 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.9902. Min Act: -0.1700
Data Index: 6786865 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.9902. Min Act: -0.1700
Data Index: 2615511 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.9589. Min Act: -0.1700
Data Index: 1039490 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.9589. Min Act: -0.1700
Data Index: 8617271 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.9277. Min Act: -0.1700
Data Index: 7537460 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.8964. Min Act: -0.1700
Data Index: 2952314 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.8964. Min Act: -0.1700
Data Index: 4811056 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.8339. Min Act: -0.1700
Data Index: 2703638 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.8339. Min Act: -0.1700
Data Index: 307045 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.8027. Min Act: -0.1700
Data Index: 650895 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8964. Min Range: -7.8964
Max Act: 6.8027. Min Act: -0.1700
Data Index: 3090625 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19