Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6058 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1193. Min Range: -6.1193
Max Act: 6.1193. Min Act: -0.1700
Data Index: 7915269 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.9943. Min Act: -0.1700
Data Index: 7205072 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.8380. Min Act: -0.1700
Data Index: 8049389 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.7755. Min Act: -0.1700
Data Index: 5226783 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.7443. Min Act: -0.1700
Data Index: 7106 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.7443. Min Act: -0.1700
Data Index: 673391 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.7443. Min Act: -0.1700
Data Index: 8049390 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6818. Min Act: -0.1700
Data Index: 563583 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6818. Min Act: -0.1700
Data Index: 69985 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6818. Min Act: -0.1700
Data Index: 4991727 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6505. Min Act: -0.1700
Data Index: 8758922 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6505. Min Act: -0.1700
Data Index: 8380362 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6193. Min Act: -0.1700
Data Index: 1752577 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.6193. Min Act: -0.1700
Data Index: 1611329 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.5880. Min Act: -0.1700
Data Index: 7645763 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.5880. Min Act: -0.1700
Data Index: 378751 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.5568. Min Act: -0.1700
Data Index: 6932582 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.5568. Min Act: -0.1700
Data Index: 5702499 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.5568. Min Act: -0.1700
Data Index: 3984704 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1193. Min Range: -6.1193
Max Act: 5.5255. Min Act: -0.1700
Data Index: 5326470 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19