Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 740 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.9851. Min Act: -0.1700
Data Index: 2981470 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.9226. Min Act: -0.1700
Data Index: 3385551 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.9539. Min Act: -0.1700
Data Index: 7629958 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.9226. Min Act: -0.1700
Data Index: 4969476 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.8601. Min Act: -0.1700
Data Index: 3976717 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.8289. Min Act: -0.1700
Data Index: 7364085 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.8601. Min Act: -0.1700
Data Index: 6175905 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7664. Min Act: -0.1700
Data Index: 149862 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7664. Min Act: -0.1700
Data Index: 1824511 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7664. Min Act: -0.1700
Data Index: 6433759 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7039. Min Act: -0.1700
Data Index: 5429006 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7664. Min Act: -0.1700
Data Index: 7562490 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.6726. Min Act: -0.1700
Data Index: 2773904 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7351. Min Act: -0.1700
Data Index: 5445440 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7039. Min Act: -0.1700
Data Index: 4851089 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.7039. Min Act: -0.1700
Data Index: 5034010 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.6726. Min Act: -0.1700
Data Index: 430116 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.6726. Min Act: -0.1700
Data Index: 3250271 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.6414. Min Act: -0.1700
Data Index: 6305186 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9851. Min Range: -6.9851
Max Act: 6.6726. Min Act: -0.1700
Data Index: 1916212 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19