Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.8413. Min Act: -0.1700
Data Index: 482716 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.7163. Min Act: -0.1700
Data Index: 2559744 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.6850. Min Act: -0.1700
Data Index: 4098253 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.5288. Min Act: -0.1700
Data Index: 4287169 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.5288. Min Act: -0.1700
Data Index: 7545255 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.5288. Min Act: -0.1700
Data Index: 476233 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.5288. Min Act: -0.1700
Data Index: 4477967 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.4663. Min Act: -0.1700
Data Index: 4059157 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.4038. Min Act: -0.1700
Data Index: 5047842 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.4350. Min Act: -0.1700
Data Index: 2425077 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.4038. Min Act: -0.1700
Data Index: 5668615 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.4038. Min Act: -0.1700
Data Index: 8328308 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3725. Min Act: -0.1700
Data Index: 7293029 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3725. Min Act: -0.1700
Data Index: 458664 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 237704 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 7836703 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 4351381 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 3990750 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3413. Min Act: -0.1700
Data Index: 4673892 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8413. Min Range: -5.8413
Max Act: 5.3100. Min Act: -0.1700
Data Index: 7260897 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19