Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0770. Min Range: -7.0770
Max Act: 7.0770. Min Act: -0.1700
Data Index: 3370688 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.8895. Min Act: -0.1700
Data Index: 1314216 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.8582. Min Act: -0.1700
Data Index: 7660010 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.8270. Min Act: -0.1700
Data Index: 6204084 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.7645. Min Act: -0.1700
Data Index: 501248 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.7332. Min Act: -0.1700
Data Index: 3161164 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.7332. Min Act: -0.1700
Data Index: 8166851 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.7020. Min Act: -0.1700
Data Index: 4798570 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.6707. Min Act: -0.1700
Data Index: 6579766 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.6707. Min Act: -0.1700
Data Index: 7716795 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.7020. Min Act: -0.1700
Data Index: 808398 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.6707. Min Act: -0.1700
Data Index: 1238414 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.6395. Min Act: -0.1700
Data Index: 8362634 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.6395. Min Act: -0.1700
Data Index: 4587031 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.5770. Min Act: -0.1700
Data Index: 1280213 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.5770. Min Act: -0.1700
Data Index: 528515 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.5145. Min Act: -0.1700
Data Index: 7011594 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.5457. Min Act: -0.1700
Data Index: 3483975 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.5457. Min Act: -0.1700
Data Index: 5919802 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0770. Min Range: -7.0770
Max Act: 6.5457. Min Act: -0.1700
Data Index: 2547948 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19