Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.6316. Min Act: -0.1700
Data Index: 3365579 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.5066. Min Act: -0.1700
Data Index: 8476109 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6181800 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.3503. Min Act: -0.1700
Data Index: 863996 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2878. Min Act: -0.1700
Data Index: 5532766 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2566. Min Act: -0.1700
Data Index: 4671123 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2253. Min Act: -0.1700
Data Index: 7535504 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2566. Min Act: -0.1700
Data Index: 1179894 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2253. Min Act: -0.1700
Data Index: 4240860 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6666140 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1628. Min Act: -0.1700
Data Index: 404041 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2566. Min Act: -0.1700
Data Index: 1689311 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.2253. Min Act: -0.1700
Data Index: 8627671 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1316. Min Act: -0.1700
Data Index: 2825427 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1628. Min Act: -0.1700
Data Index: 4891967 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1316. Min Act: -0.1700
Data Index: 6007779 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1316. Min Act: -0.1700
Data Index: 232744 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1316. Min Act: -0.1700
Data Index: 5366255 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.1003. Min Act: -0.1700
Data Index: 2168419 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6316. Min Range: -6.6316
Max Act: 6.0691. Min Act: -0.1700
Data Index: 3850711 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19