Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.6212. Min Act: -0.1700
Data Index: 8087958 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.5899. Min Act: -0.1700
Data Index: 2098465 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.5274. Min Act: -0.1700
Data Index: 6202949 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.5274. Min Act: -0.1700
Data Index: 6627354 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.5274. Min Act: -0.1700
Data Index: 7027532 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.5274. Min Act: -0.1700
Data Index: 1277219 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4962. Min Act: -0.1700
Data Index: 8701664 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4962. Min Act: -0.1700
Data Index: 6520569 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.5274. Min Act: -0.1699
Data Index: 3525718 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4962. Min Act: -0.1700
Data Index: 500652 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4962. Min Act: -0.1700
Data Index: 1376776 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4962. Min Act: -0.1696
Data Index: 4123764 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3342388 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4649. Min Act: -0.1700
Data Index: 7079251 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4649. Min Act: -0.1700
Data Index: 2733970 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3534424 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4649. Min Act: -0.1699
Data Index: 5978656 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4649. Min Act: -0.1700
Data Index: 1045767 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4337. Min Act: -0.1700
Data Index: 2209422 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6212. Min Range: -5.6212
Max Act: 5.4337. Min Act: -0.1700
Data Index: 1284672 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19