Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5336 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.5523. Min Act: -0.1700
Data Index: 4549889 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.5053. Min Act: -0.1700
Data Index: 4534337 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.5210. Min Act: -0.1700
Data Index: 3999592 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.5053. Min Act: -0.1700
Data Index: 6151498 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.4583. Min Act: -0.1700
Data Index: 4200908 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.4583. Min Act: -0.1700
Data Index: 8340919 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.4113. Min Act: -0.1700
Data Index: 1530697 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.4270. Min Act: -0.1700
Data Index: 1434101 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.4113. Min Act: -0.1700
Data Index: 7565318 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3956. Min Act: -0.1700
Data Index: 5941299 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3800. Min Act: -0.1700
Data Index: 7590497 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3956. Min Act: -0.1700
Data Index: 2569765 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3800. Min Act: -0.1700
Data Index: 1455389 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3800. Min Act: -0.1700
Data Index: 4549614 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3800. Min Act: -0.1700
Data Index: 2901007 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3956. Min Act: -0.1700
Data Index: 5257138 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3800. Min Act: -0.1700
Data Index: 4636322 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3643. Min Act: -0.1700
Data Index: 1979797 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3800. Min Act: -0.1700
Data Index: 4903885 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5523. Min Range: -3.5523
Max Act: 3.3643. Min Act: -0.1700
Data Index: 168894 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19