Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.8609. Min Act: -0.1700
Data Index: 6112179 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.7046. Min Act: -0.1700
Data Index: 279562 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.6421. Min Act: -0.1700
Data Index: 5850547 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.5796. Min Act: -0.1700
Data Index: 6981245 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.4546. Min Act: -0.1700
Data Index: 3897700 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.4234. Min Act: -0.1700
Data Index: 247902 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.4234. Min Act: -0.1700
Data Index: 6858093 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.3921. Min Act: -0.1700
Data Index: 8393636 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.3296. Min Act: -0.1700
Data Index: 1162775 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.3296. Min Act: -0.1700
Data Index: 5466016 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2984. Min Act: -0.1700
Data Index: 306099 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.3296. Min Act: -0.1700
Data Index: 7601368 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2984. Min Act: -0.1700
Data Index: 420663 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2984. Min Act: -0.1700
Data Index: 7565912 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2067041 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1470802 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 3930038 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 7269646 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 3285203 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8609. Min Range: -6.8609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 1358104 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19