Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3756 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.7039. Min Act: -0.1700
Data Index: 2609229 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.5164. Min Act: -0.1700
Data Index: 169232 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.2976. Min Act: -0.1700
Data Index: 8126428 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.1726. Min Act: -0.1700
Data Index: 1498020 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.2039. Min Act: -0.1700
Data Index: 3167612 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.1726. Min Act: -0.1700
Data Index: 222825 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.1414. Min Act: -0.1700
Data Index: 2955008 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.1101. Min Act: -0.1700
Data Index: 5006631 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7039. Min Range: -7.7039
Max Act: 7.1414. Min Act: -0.1700
Data Index: 393393 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.9226. Min Act: -0.1700
Data Index: 1278204 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.8601. Min Act: -0.1700
Data Index: 2377764 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.8601. Min Act: -0.1700
Data Index: 8781818 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.8914. Min Act: -0.1700
Data Index: 5450031 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.8601. Min Act: -0.1700
Data Index: 5893561 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.8289. Min Act: -0.1700
Data Index: 5254444 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.8289. Min Act: -0.1700
Data Index: 3918484 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.7976. Min Act: -0.1700
Data Index: 3615498 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.7351. Min Act: -0.1700
Data Index: 2153513 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.7664. Min Act: -0.1700
Data Index: 7157766 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7039. Min Range: -7.7039
Max Act: 6.7351. Min Act: -0.1700
Data Index: 4512663 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19