Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4537 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.8790. Min Act: -0.1700
Data Index: 8695680 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.6603. Min Act: -0.1700
Data Index: 3071395 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.6290. Min Act: -0.1700
Data Index: 7280993 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5978. Min Act: -0.1700
Data Index: 8641058 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5353. Min Act: -0.1700
Data Index: 8760382 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6002979 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5040. Min Act: -0.1700
Data Index: 3406186 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5040. Min Act: -0.1700
Data Index: 7280994 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5040. Min Act: -0.1700
Data Index: 8641056 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5040. Min Act: -0.1700
Data Index: 4644875 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.5353. Min Act: -0.1700
Data Index: 2896815 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.4415. Min Act: -0.1700
Data Index: 5415807 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.4415. Min Act: -0.1700
Data Index: 7472965 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.3790. Min Act: -0.1700
Data Index: 6147071 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.4103. Min Act: -0.1700
Data Index: 1998443 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.3478. Min Act: -0.1700
Data Index: 8276184 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.3165. Min Act: -0.1700
Data Index: 8346893 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.3478. Min Act: -0.1700
Data Index: 900199 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.3478. Min Act: -0.1700
Data Index: 4799893 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8790. Min Range: -5.8790
Max Act: 5.3165. Min Act: -0.1700
Data Index: 664340 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19