Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4873 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5679. Min Range: -8.5679
Max Act: 8.5679. Min Act: -0.1700
Data Index: 1898959 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5679. Min Range: -8.5679
Max Act: 8.1304. Min Act: -0.1699
Data Index: 7320667 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5679. Min Range: -8.5679
Max Act: 8.0679. Min Act: -0.1700
Data Index: 5370368 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.9429. Min Act: -0.1700
Data Index: 3960560 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.9429. Min Act: -0.1700
Data Index: 2242174 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.9429. Min Act: -0.1700
Data Index: 6725700 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.8804. Min Act: -0.1700
Data Index: 5778223 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.8804. Min Act: -0.1700
Data Index: 4679989 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.8804. Min Act: -0.1700
Data Index: 1211384 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.8804. Min Act: -0.1700
Data Index: 8706236 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.8804. Min Act: -0.1700
Data Index: 7891620 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.8179. Min Act: -0.1700
Data Index: 116063 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.7554. Min Act: -0.1700
Data Index: 4147464 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.7554. Min Act: -0.1700
Data Index: 4791652 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.7242. Min Act: -0.1700
Data Index: 6414414 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.7242. Min Act: -0.1700
Data Index: 5005868 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.6929. Min Act: -0.1700
Data Index: 2763044 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.6617. Min Act: -0.1700
Data Index: 3961530 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.6929. Min Act: -0.1700
Data Index: 4615925 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5679. Min Range: -8.5679
Max Act: 7.6929. Min Act: -0.1700
Data Index: 5219610 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19