Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.2242. Min Act: -0.1700
Data Index: 6353642 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.1770. Min Act: -0.1700
Data Index: 4077065 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.1456. Min Act: -0.1700
Data Index: 7017247 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.1298. Min Act: -0.1700
Data Index: 2226065 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.1456. Min Act: -0.1700
Data Index: 6056142 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.1141. Min Act: -0.1700
Data Index: 8307714 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0825. Min Act: -0.1700
Data Index: 8050550 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0983. Min Act: -0.1700
Data Index: 5454095 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0825. Min Act: -0.1700
Data Index: 8697621 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0668. Min Act: -0.1700
Data Index: 5227221 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0668. Min Act: -0.1700
Data Index: 7573855 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0668. Min Act: -0.1700
Data Index: 1366284 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0668. Min Act: -0.1700
Data Index: 117281 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0352. Min Act: -0.1700
Data Index: 3919042 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0510. Min Act: -0.1700
Data Index: 5101499 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0510. Min Act: -0.1700
Data Index: 8345783 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0510. Min Act: -0.1700
Data Index: 4602760 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0510. Min Act: -0.1700
Data Index: 8756529 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0510. Min Act: -0.1700
Data Index: 6438971 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2242. Min Range: -3.2242
Max Act: 3.0510. Min Act: -0.1700
Data Index: 1955232 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19