Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.7818. Min Act: -0.1700
Data Index: 7771822 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.7818. Min Act: -0.1700
Data Index: 1227102 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.7506. Min Act: -0.1700
Data Index: 5809284 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.7193. Min Act: -0.1700
Data Index: 2168039 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.7193. Min Act: -0.1700
Data Index: 1303811 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.7193. Min Act: -0.1700
Data Index: 1227104 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6881. Min Act: -0.1700
Data Index: 7771819 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6881. Min Act: -0.1700
Data Index: 3592500 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6568. Min Act: -0.1700
Data Index: 2140047 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6256. Min Act: -0.1700
Data Index: 2077806 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6256. Min Act: -0.1700
Data Index: 1174197 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6568. Min Act: -0.1700
Data Index: 5654128 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3011011 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.6568. Min Act: -0.1700
Data Index: 3400351 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.5943. Min Act: -0.1700
Data Index: 6560564 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.5943. Min Act: -0.1700
Data Index: 5809282 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.5943. Min Act: -0.1700
Data Index: 163941 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.5943. Min Act: -0.1700
Data Index: 7353969 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.5943. Min Act: -0.1700
Data Index: 4303566 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7818. Min Range: -4.7818
Max Act: 4.5943. Min Act: -0.1700
Data Index: 4516780 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19