Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4262 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6933. Min Act: -0.1700
Data Index: 5901200 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6933. Min Act: -0.1700
Data Index: 4886777 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6933. Min Act: -0.1700
Data Index: 3611568 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6773. Min Act: -0.1700
Data Index: 3611567 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6452. Min Act: -0.1700
Data Index: 6186879 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6292. Min Act: -0.1700
Data Index: 7161798 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6292. Min Act: -0.1700
Data Index: 2796678 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.6292. Min Act: -0.1700
Data Index: 7514654 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5809. Min Act: -0.1700
Data Index: 5971813 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5809. Min Act: -0.1700
Data Index: 6368000 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5486. Min Act: -0.1700
Data Index: 1794138 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5648. Min Act: -0.1700
Data Index: 7806523 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5809. Min Act: -0.1700
Data Index: 3611557 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5486. Min Act: -0.1700
Data Index: 4440291 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5486. Min Act: -0.1700
Data Index: 3809508 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5486. Min Act: -0.1700
Data Index: 4886780 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5325. Min Act: -0.1700
Data Index: 3611562 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5163. Min Act: -0.1700
Data Index: 1923433 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5163. Min Act: -0.1700
Data Index: 7987932 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6933. Min Range: -2.6933
Max Act: 2.5325. Min Act: -0.1700
Data Index: 7538817 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19