Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 613 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3659. Min Act: -0.1700
Data Index: 6214475 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3659. Min Act: -0.1700
Data Index: 3096590 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3659. Min Act: -0.1700
Data Index: 5959254 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 1345318 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 3745246 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 3429590 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 2474303 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3034. Min Act: -0.1700
Data Index: 6010439 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 4500209 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 8270798 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3034. Min Act: -0.1700
Data Index: 7887897 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3034. Min Act: -0.1700
Data Index: 585421 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3034. Min Act: -0.1700
Data Index: 3799583 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3347. Min Act: -0.1700
Data Index: 5666545 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.3034. Min Act: -0.1700
Data Index: 8819609 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.2722. Min Act: -0.1700
Data Index: 7045699 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.2722. Min Act: -0.1700
Data Index: 6046550 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.2722. Min Act: -0.1700
Data Index: 7972578 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.2722. Min Act: -0.1700
Data Index: 7974324 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3659. Min Range: -4.3659
Max Act: 4.2722. Min Act: -0.1700
Data Index: 81671 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19