Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1830 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 8658575 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 2781037 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 6591736 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.2788. Min Act: -0.1700
Data Index: 294569 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.2163. Min Act: -0.1700
Data Index: 5377107 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.1538. Min Act: -0.1700
Data Index: 5594974 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.1538. Min Act: -0.1700
Data Index: 5335529 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.1226. Min Act: -0.1700
Data Index: 4119412 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.1226. Min Act: -0.1700
Data Index: 6613510 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.1226. Min Act: -0.1700
Data Index: 2480529 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0913. Min Act: -0.1700
Data Index: 920101 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0913. Min Act: -0.1700
Data Index: 4425627 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0913. Min Act: -0.1700
Data Index: 5566143 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0913. Min Act: -0.1700
Data Index: 4078908 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0913. Min Act: -0.1700
Data Index: 5602600 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0601. Min Act: -0.1700
Data Index: 3738029 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0288. Min Act: -0.1700
Data Index: 5897902 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0288. Min Act: -0.1700
Data Index: 943490 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3413. Min Range: -5.3413
Max Act: 5.0288. Min Act: -0.1700
Data Index: 8803577 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3413. Min Range: -5.3413
Max Act: 4.9663. Min Act: -0.1700
Data Index: 2543142 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19