Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 704 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.2215. Min Act: -0.1700
Data Index: 3497982 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.1902. Min Act: -0.1700
Data Index: 2033693 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.2215. Min Act: -0.1700
Data Index: 6361528 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.1590. Min Act: -0.1700
Data Index: 2967421 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.1277. Min Act: -0.1700
Data Index: 1731549 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.0965. Min Act: -0.1700
Data Index: 80074 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.0027. Min Act: -0.1700
Data Index: 5960617 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.0027. Min Act: -0.1700
Data Index: 906686 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.0652. Min Act: -0.1700
Data Index: 4451480 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.9715. Min Act: -0.1700
Data Index: 7727087 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.9715. Min Act: -0.1700
Data Index: 7013493 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2215. Min Range: -5.2215
Max Act: 5.0340. Min Act: -0.1700
Data Index: 1770841 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.9715. Min Act: -0.1700
Data Index: 4994405 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.9402. Min Act: -0.1700
Data Index: 8463587 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.8777. Min Act: -0.1700
Data Index: 5773102 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.8777. Min Act: -0.1700
Data Index: 884984 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.8777. Min Act: -0.1700
Data Index: 3841121 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.8777. Min Act: -0.1700
Data Index: 2277526 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.8152. Min Act: -0.1700
Data Index: 2834890 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2215. Min Range: -5.2215
Max Act: 4.8152. Min Act: -0.1700
Data Index: 3567135 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19