Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.8443. Min Act: -0.1700
Data Index: 407367 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.7193. Min Act: -0.1700
Data Index: 1667291 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.7193. Min Act: -0.1700
Data Index: 2115673 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.6255. Min Act: -0.1700
Data Index: 495751 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.5630. Min Act: -0.1700
Data Index: 7934287 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.5943. Min Act: -0.1700
Data Index: 5323446 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.5630. Min Act: -0.1700
Data Index: 3303364 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.5318. Min Act: -0.1700
Data Index: 8179139 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.5005. Min Act: -0.1700
Data Index: 6902795 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4380. Min Act: -0.1700
Data Index: 301546 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4693. Min Act: -0.1700
Data Index: 7075558 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4068. Min Act: -0.1700
Data Index: 8254495 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4693. Min Act: -0.1700
Data Index: 1008644 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4380. Min Act: -0.1700
Data Index: 7421101 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4068. Min Act: -0.1700
Data Index: 993762 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4068. Min Act: -0.1700
Data Index: 8602311 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.4068. Min Act: -0.1700
Data Index: 1983418 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.3755. Min Act: -0.1700
Data Index: 910065 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.3755. Min Act: -0.1700
Data Index: 3533070 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8443. Min Range: -6.8443
Max Act: 6.3443. Min Act: -0.1700
Data Index: 4544474 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19