Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.9228. Min Act: -0.1700
Data Index: 2073622 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.8290. Min Act: -0.1700
Data Index: 3683267 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.8603. Min Act: -0.1700
Data Index: 3846925 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7977. Min Act: -0.1700
Data Index: 4453004 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7665. Min Act: -0.1700
Data Index: 6639206 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7665. Min Act: -0.1700
Data Index: 1281645 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7352. Min Act: -0.1700
Data Index: 6829456 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7665. Min Act: -0.1700
Data Index: 4193701 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7665. Min Act: -0.1700
Data Index: 4210937 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7352. Min Act: -0.1700
Data Index: 3359788 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7039. Min Act: -0.1700
Data Index: 6397058 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7352. Min Act: -0.1700
Data Index: 2428563 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7039. Min Act: -0.1700
Data Index: 5206874 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7039. Min Act: -0.1700
Data Index: 7618827 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7039. Min Act: -0.1700
Data Index: 6829455 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.6726. Min Act: -0.1700
Data Index: 1511365 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.6726. Min Act: -0.1700
Data Index: 3986605 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7039. Min Act: -0.1700
Data Index: 6330122 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.7039. Min Act: -0.1700
Data Index: 3846926 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9228. Min Range: -3.9228
Max Act: 3.6726. Min Act: -0.1700
Data Index: 3616088 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19