Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.9674. Min Act: -0.1700
Data Index: 2940045 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.8424. Min Act: -0.1700
Data Index: 1101737 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.8112. Min Act: -0.1700
Data Index: 6714471 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.8112. Min Act: -0.1700
Data Index: 1736793 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.7487. Min Act: -0.1700
Data Index: 1848459 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.7174. Min Act: -0.1700
Data Index: 947034 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.7174. Min Act: -0.1700
Data Index: 5364404 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.6237. Min Act: -0.1700
Data Index: 6833830 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5924. Min Act: -0.1700
Data Index: 6444731 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5924. Min Act: -0.1700
Data Index: 6190660 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5612. Min Act: -0.1700
Data Index: 6967452 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5299. Min Act: -0.1700
Data Index: 8208229 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5299. Min Act: -0.1700
Data Index: 7311936 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5299. Min Act: -0.1700
Data Index: 6446285 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5299. Min Act: -0.1700
Data Index: 1734770 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.5299. Min Act: -0.1700
Data Index: 7244810 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.4987. Min Act: -0.1700
Data Index: 2261532 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.4987. Min Act: -0.1700
Data Index: 2796315 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.4674. Min Act: -0.1700
Data Index: 6500005 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9674. Min Range: -6.9674
Max Act: 6.4987. Min Act: -0.1700
Data Index: 2084243 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19