Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.3238. Min Act: -0.1700
Data Index: 7747832 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.3238. Min Act: -0.1700
Data Index: 7601947 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.2613. Min Act: -0.1700
Data Index: 3456776 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.1988. Min Act: -0.1700
Data Index: 8461333 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.1988. Min Act: -0.1700
Data Index: 3764899 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.1363. Min Act: -0.1700
Data Index: 2066505 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.1363. Min Act: -0.1700
Data Index: 3122942 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.0113. Min Act: -0.1700
Data Index: 4127383 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.0113. Min Act: -0.1700
Data Index: 6763231 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3238. Min Range: -8.3238
Max Act: 8.0113. Min Act: -0.1700
Data Index: 7276641 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8863. Min Act: -0.1700
Data Index: 3399297 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.9488. Min Act: -0.1700
Data Index: 8809810 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.9488. Min Act: -0.1700
Data Index: 2713556 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8863. Min Act: -0.1700
Data Index: 5521370 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8863. Min Act: -0.1700
Data Index: 7452580 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.9488. Min Act: -0.1700
Data Index: 2267064 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8863. Min Act: -0.1700
Data Index: 8417641 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8863. Min Act: -0.1700
Data Index: 6145649 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8863. Min Act: -0.1700
Data Index: 5586165 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3238. Min Range: -8.3238
Max Act: 7.8238. Min Act: -0.1700
Data Index: 3167997 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19