Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4299 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.9465. Min Act: -0.1700
Data Index: 2302702 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.9153. Min Act: -0.1700
Data Index: 6969660 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.8840. Min Act: -0.1700
Data Index: 4887180 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.7590. Min Act: -0.1700
Data Index: 3605260 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.7903. Min Act: -0.1700
Data Index: 149239 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.7903. Min Act: -0.1700
Data Index: 5978278 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.7278. Min Act: -0.1700
Data Index: 3973869 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.7278. Min Act: -0.1700
Data Index: 2362759 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.7278. Min Act: -0.1700
Data Index: 3969866 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6965. Min Act: -0.1700
Data Index: 584330 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6965. Min Act: -0.1700
Data Index: 6837136 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6965. Min Act: -0.1700
Data Index: 534961 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6965. Min Act: -0.1700
Data Index: 8439976 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6653. Min Act: -0.1700
Data Index: 607276 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6653. Min Act: -0.1700
Data Index: 2955350 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6653. Min Act: -0.1700
Data Index: 8120806 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6340. Min Act: -0.1700
Data Index: 2151631 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6653. Min Act: -0.1700
Data Index: 3432122 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6340. Min Act: -0.1700
Data Index: 6216853 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9465. Min Range: -4.9465
Max Act: 4.6340. Min Act: -0.1700
Data Index: 4319949 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19