Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3943 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4488. Min Range: -9.4488
Max Act: 9.4488. Min Act: -0.1700
Data Index: 4258196 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.8238. Min Act: -0.1700
Data Index: 2034099 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.7613. Min Act: -0.1700
Data Index: 6031870 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.5738. Min Act: -0.1700
Data Index: 2372079 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.5738. Min Act: -0.1700
Data Index: 4089614 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.4488. Min Act: -0.1700
Data Index: 164026 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.3863. Min Act: -0.1700
Data Index: 7409107 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.3238. Min Act: -0.1700
Data Index: 3146015 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.3238. Min Act: -0.1700
Data Index: 7047311 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.3238. Min Act: -0.1700
Data Index: 6703817 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1988. Min Act: -0.1700
Data Index: 1494033 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1988. Min Act: -0.1700
Data Index: 487297 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1988. Min Act: -0.1700
Data Index: 422800 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1363. Min Act: -0.1700
Data Index: 5299043 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1363. Min Act: -0.1700
Data Index: 6225743 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1363. Min Act: -0.1700
Data Index: 4634230 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.1363. Min Act: -0.1700
Data Index: 7145187 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.0738. Min Act: -0.1700
Data Index: 2385903 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.0738. Min Act: -0.1700
Data Index: 7879454 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4488. Min Range: -9.4488
Max Act: 8.0738. Min Act: -0.1700
Data Index: 3292628 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19