Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6380 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7113. Min Range: -9.7113
Max Act: 9.7113. Min Act: -0.1700
Data Index: 3268470 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.9613. Min Act: -0.1700
Data Index: 6650718 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.9613. Min Act: -0.1700
Data Index: 198947 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.8988. Min Act: -0.1700
Data Index: 8017281 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.8363. Min Act: -0.1700
Data Index: 8215549 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.7738. Min Act: -0.1700
Data Index: 4189256 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.7738. Min Act: -0.1700
Data Index: 4892021 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.7738. Min Act: -0.1700
Data Index: 433900 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.5238. Min Act: -0.1700
Data Index: 1099000 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3988. Min Act: -0.1700
Data Index: 3572429 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.4613. Min Act: -0.1700
Data Index: 7036885 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3988. Min Act: -0.1700
Data Index: 4600893 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3363. Min Act: -0.1700
Data Index: 6383348 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3363. Min Act: -0.1700
Data Index: 7744354 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3363. Min Act: -0.1700
Data Index: 1648292 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3363. Min Act: -0.1700
Data Index: 4785215 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3363. Min Act: -0.1700
Data Index: 1648288 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.3363. Min Act: -0.1700
Data Index: 1049602 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.2738. Min Act: -0.1700
Data Index: 8500882 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7113. Min Range: -9.7113
Max Act: 8.2113. Min Act: -0.1700
Data Index: 2762490 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19