Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.6863. Min Act: -0.1700
Data Index: 526714 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.6550. Min Act: -0.1700
Data Index: 5799986 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.6550. Min Act: -0.1700
Data Index: 2022768 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.6237. Min Act: -0.1700
Data Index: 6658706 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.6237. Min Act: -0.1700
Data Index: 811812 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.6237. Min Act: -0.1700
Data Index: 4865103 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.5298. Min Act: -0.1700
Data Index: 8806708 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.5298. Min Act: -0.1700
Data Index: 29629 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.5298. Min Act: -0.1700
Data Index: 2685839 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.5298. Min Act: -0.1700
Data Index: 5321257 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4984. Min Act: -0.1700
Data Index: 3122270 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4984. Min Act: -0.1700
Data Index: 4579950 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4358. Min Act: -0.1700
Data Index: 2414207 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4671. Min Act: -0.1700
Data Index: 6110292 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4358. Min Act: -0.1700
Data Index: 218476 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4671. Min Act: -0.1700
Data Index: 7952332 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4358. Min Act: -0.1700
Data Index: 3102349 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4671. Min Act: -0.1700
Data Index: 5176536 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4358. Min Act: -0.1700
Data Index: 714051 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6863. Min Range: -3.6863
Max Act: 3.4358. Min Act: -0.1700
Data Index: 2245818 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19