Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1431. Min Range: -10.1431
Max Act: 10.1431. Min Act: -0.1700
Data Index: 3959582 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.7681. Min Act: -0.1700
Data Index: 6429309 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.7056. Min Act: -0.1700
Data Index: 713115 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.5806. Min Act: -0.1700
Data Index: 529893 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.6431. Min Act: -0.1700
Data Index: 6797456 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.5181. Min Act: -0.1700
Data Index: 2678647 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.4556. Min Act: -0.1700
Data Index: 857382 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3931. Min Act: -0.1700
Data Index: 1040645 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3931. Min Act: -0.1700
Data Index: 3097128 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 3930063 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 2678646 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 2678649 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3931. Min Act: -0.1700
Data Index: 5064319 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 7091276 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.2681. Min Act: -0.1700
Data Index: 6577178 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.3306. Min Act: -0.1700
Data Index: 4094221 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.2681. Min Act: -0.1700
Data Index: 8726115 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 1453465 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.2681. Min Act: -0.1700
Data Index: 722092 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1431. Min Range: -10.1431
Max Act: 9.2056. Min Act: -0.1700
Data Index: 2924343 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19