Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 782 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2409. Min Range: -5.2409
Max Act: 5.2409. Min Act: -0.1700
Data Index: 7156461 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2409. Min Range: -5.2409
Max Act: 5.1159. Min Act: -0.1700
Data Index: 3212046 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2409. Min Range: -5.2409
Max Act: 5.0847. Min Act: -0.1700
Data Index: 6135729 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2409. Min Range: -5.2409
Max Act: 5.0534. Min Act: -0.1700
Data Index: 2195327 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2409. Min Range: -5.2409
Max Act: 5.0222. Min Act: -0.1700
Data Index: 7098383 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2409. Min Range: -5.2409
Max Act: 5.0222. Min Act: -0.1700
Data Index: 312486 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.9597. Min Act: -0.1700
Data Index: 2691517 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.9284. Min Act: -0.1700
Data Index: 990505 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.9284. Min Act: -0.1700
Data Index: 1670868 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.9284. Min Act: -0.1700
Data Index: 6639425 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.9284. Min Act: -0.1700
Data Index: 4051910 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8659. Min Act: -0.1700
Data Index: 5756147 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8659. Min Act: -0.1700
Data Index: 3513288 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8347. Min Act: -0.1700
Data Index: 4112004 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8347. Min Act: -0.1700
Data Index: 339885 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8034. Min Act: -0.1700
Data Index: 5521182 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8034. Min Act: -0.1700
Data Index: 81823 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.8347. Min Act: -0.1700
Data Index: 2870638 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.7722. Min Act: -0.1700
Data Index: 3995975 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2409. Min Range: -5.2409
Max Act: 4.7409. Min Act: -0.1700
Data Index: 6152602 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19