Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.3549. Min Act: -0.1700
Data Index: 3259956 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.2611. Min Act: -0.1700
Data Index: 3804376 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.1986. Min Act: -0.1700
Data Index: 1147054 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.1049. Min Act: -0.1700
Data Index: 4923324 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0736. Min Act: -0.1700
Data Index: 5150071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0736. Min Act: -0.1700
Data Index: 7858446 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0111. Min Act: -0.1700
Data Index: 1271584 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9799. Min Act: -0.1700
Data Index: 1008262 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8861. Min Act: -0.1700
Data Index: 2043437 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8549. Min Act: -0.1700
Data Index: 2848643 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.7924. Min Act: -0.1700
Data Index: 5362281 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.7611. Min Act: -0.1700
Data Index: 5233274 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.7611. Min Act: -0.1700
Data Index: 1269187 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.7924. Min Act: -0.1700
Data Index: 6198372 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.6674. Min Act: -0.1700
Data Index: 7228933 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.6986. Min Act: -0.1700
Data Index: 8019236 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.6986. Min Act: -0.1700
Data Index: 5462647 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.7299. Min Act: -0.1700
Data Index: 1279192 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.6986. Min Act: -0.1700
Data Index: 684312 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.6674. Min Act: -0.1700
Data Index: 1695292 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19