Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.7313. Min Act: -0.1700
Data Index: 633118 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 5980097 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4813. Min Act: -0.1700
Data Index: 1507253 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4813. Min Act: -0.1700
Data Index: 8285528 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 4574211 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4188. Min Act: -0.1700
Data Index: 246672 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4188. Min Act: -0.1700
Data Index: 7330434 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4500. Min Act: -0.1700
Data Index: 110292 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4188. Min Act: -0.1700
Data Index: 6996276 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.3250. Min Act: -0.1700
Data Index: 5264823 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.3563. Min Act: -0.1700
Data Index: 1220258 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.3250. Min Act: -0.1700
Data Index: 7409777 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2938. Min Act: -0.1700
Data Index: 7032756 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2938. Min Act: -0.1700
Data Index: 5525520 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2938. Min Act: -0.1700
Data Index: 7608228 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2625. Min Act: -0.1700
Data Index: 7596572 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2625. Min Act: -0.1700
Data Index: 2941709 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2625. Min Act: -0.1700
Data Index: 571067 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2938. Min Act: -0.1700
Data Index: 2169515 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.2313. Min Act: -0.1700
Data Index: 573403 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19