Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5818 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.7465. Min Act: -0.1700
Data Index: 5041273 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.4653. Min Act: -0.1700
Data Index: 3584049 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.4653. Min Act: -0.1700
Data Index: 2986211 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.4340. Min Act: -0.1700
Data Index: 4937116 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.3403. Min Act: -0.1700
Data Index: 2651800 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.2778. Min Act: -0.1700
Data Index: 5985821 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.2153. Min Act: -0.1700
Data Index: 7705275 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.1215. Min Act: -0.1700
Data Index: 1855059 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.1528. Min Act: -0.1700
Data Index: 4361051 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.1840. Min Act: -0.1700
Data Index: 113277 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.1215. Min Act: -0.1700
Data Index: 8039898 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.1215. Min Act: -0.1700
Data Index: 549071 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.1528. Min Act: -0.1700
Data Index: 1010991 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0903. Min Act: -0.1700
Data Index: 6495234 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0903. Min Act: -0.1700
Data Index: 657653 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0903. Min Act: -0.1700
Data Index: 461605 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0590. Min Act: -0.1700
Data Index: 2833654 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0278. Min Act: -0.1700
Data Index: 2398314 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0278. Min Act: -0.1700
Data Index: 13789 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7465. Min Range: -7.7465
Max Act: 7.0278. Min Act: -0.1700
Data Index: 4610760 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19