Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2409 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.1108. Min Act: -0.1700
Data Index: 3963872 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.1108. Min Act: -0.1700
Data Index: 7311768 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.1108. Min Act: -0.1700
Data Index: 421299 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0796. Min Act: -0.1700
Data Index: 7338688 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0796. Min Act: -0.1700
Data Index: 7156844 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0796. Min Act: -0.1700
Data Index: 5787969 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 2870209 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 7450667 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 4040159 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 5115490 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 6246743 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 5839714 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0483. Min Act: -0.1700
Data Index: 5979849 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0171. Min Act: -0.1700
Data Index: 7319678 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0171. Min Act: -0.1700
Data Index: 3524671 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0171. Min Act: -0.1700
Data Index: 1824520 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0171. Min Act: -0.1700
Data Index: 166334 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0171. Min Act: -0.1700
Data Index: 1102720 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.0171. Min Act: -0.1700
Data Index: 4008425 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.9858. Min Act: -0.1700
Data Index: 3076241 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19