Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5147 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0770. Min Range: -4.0770
Max Act: 4.0770. Min Act: -0.1700
Data Index: 2869032 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0770. Min Range: -4.0770
Max Act: 4.0145. Min Act: -0.1700
Data Index: 639680 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9520. Min Act: -0.1700
Data Index: 4369134 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9520. Min Act: -0.1700
Data Index: 4308369 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9207. Min Act: -0.1700
Data Index: 254800 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9207. Min Act: -0.1700
Data Index: 4440535 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9207. Min Act: -0.1700
Data Index: 2263776 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9207. Min Act: -0.1700
Data Index: 4958923 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.9207. Min Act: -0.1700
Data Index: 1158286 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8894. Min Act: -0.1700
Data Index: 7894015 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8894. Min Act: -0.1700
Data Index: 2698454 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8894. Min Act: -0.1700
Data Index: 4567843 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8582. Min Act: -0.1700
Data Index: 2713613 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8582. Min Act: -0.1700
Data Index: 6949596 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8582. Min Act: -0.1700
Data Index: 2401106 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8582. Min Act: -0.1700
Data Index: 6266950 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8582. Min Act: -0.1700
Data Index: 2473145 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.7956. Min Act: -0.1700
Data Index: 2839443 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8269. Min Act: -0.1700
Data Index: 1028121 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0770. Min Range: -4.0770
Max Act: 3.8269. Min Act: -0.1700
Data Index: 3001630 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19