Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1587 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6097640 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.6755. Min Act: -0.1700
Data Index: 383414 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.6443. Min Act: -0.1700
Data Index: 3093071 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.6443. Min Act: -0.1700
Data Index: 2884152 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.6130. Min Act: -0.1700
Data Index: 195775 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.6130. Min Act: -0.1700
Data Index: 6233105 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.6130. Min Act: -0.1700
Data Index: 1480382 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.5193. Min Act: -0.1700
Data Index: 3828607 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.4880. Min Act: -0.1700
Data Index: 6213407 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.5193. Min Act: -0.1700
Data Index: 1220262 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.4568. Min Act: -0.1700
Data Index: 6704379 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.4568. Min Act: -0.1700
Data Index: 7913495 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.4255. Min Act: -0.1700
Data Index: 8359889 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.4568. Min Act: -0.1700
Data Index: 3301168 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.3943. Min Act: -0.1700
Data Index: 4014434 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.4255. Min Act: -0.1700
Data Index: 495517 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.3943. Min Act: -0.1700
Data Index: 755139 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.3943. Min Act: -0.1700
Data Index: 4191151 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.3318. Min Act: -0.1700
Data Index: 5405349 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9255. Min Range: -4.9255
Max Act: 4.3005. Min Act: -0.1700
Data Index: 6887427 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19