Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.3042. Min Act: -0.1700
Data Index: 4306654 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.3042. Min Act: -0.1700
Data Index: 282557 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.3354. Min Act: -0.1700
Data Index: 4118914 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.3354. Min Act: -0.1700
Data Index: 5313515 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.2104. Min Act: -0.1700
Data Index: 1337838 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.1792. Min Act: -0.1700
Data Index: 8614174 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.1792. Min Act: -0.1700
Data Index: 7339742 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.1479. Min Act: -0.1700
Data Index: 7412812 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.1792. Min Act: -0.1700
Data Index: 4481147 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.1479. Min Act: -0.1700
Data Index: 1560692 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.0854. Min Act: -0.1700
Data Index: 8250040 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.0542. Min Act: -0.1700
Data Index: 1080447 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.0542. Min Act: -0.1700
Data Index: 6695572 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.0229. Min Act: -0.1700
Data Index: 4588722 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3354. Min Range: -5.3354
Max Act: 5.0229. Min Act: -0.1700
Data Index: 5633035 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3354. Min Range: -5.3354
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3361910 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3354. Min Range: -5.3354
Max Act: 4.9917. Min Act: -0.1700
Data Index: 7250978 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3354. Min Range: -5.3354
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2924901 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3354. Min Range: -5.3354
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3940897 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3354. Min Range: -5.3354
Max Act: 4.9604. Min Act: -0.1700
Data Index: 8365428 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19