Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2356. Min Range: -8.2356
Max Act: 8.2356. Min Act: -0.1700
Data Index: 6973611 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2356. Min Range: -8.2356
Max Act: 8.1731. Min Act: -0.1700
Data Index: 8072540 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2356. Min Range: -8.2356
Max Act: 8.0481. Min Act: -0.1700
Data Index: 3692773 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2356. Min Range: -8.2356
Max Act: 8.0481. Min Act: -0.1700
Data Index: 1382965 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2356. Min Range: -8.2356
Max Act: 8.0481. Min Act: -0.1700
Data Index: 839605 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9856. Min Act: -0.1700
Data Index: 3530024 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9856. Min Act: -0.1700
Data Index: 6113023 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9231. Min Act: -0.1700
Data Index: 2033022 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9231. Min Act: -0.1700
Data Index: 2953835 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9856. Min Act: -0.1700
Data Index: 6003065 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9231. Min Act: -0.1700
Data Index: 2678721 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.9231. Min Act: -0.1700
Data Index: 1453354 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.8606. Min Act: -0.1700
Data Index: 755820 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.8606. Min Act: -0.1700
Data Index: 7580827 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.8606. Min Act: -0.1700
Data Index: 6179272 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.7981. Min Act: -0.1700
Data Index: 5761338 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.7981. Min Act: -0.1700
Data Index: 2596101 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.7981. Min Act: -0.1700
Data Index: 644602 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.7356. Min Act: -0.1700
Data Index: 1837487 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2356. Min Range: -8.2356
Max Act: 7.6731. Min Act: -0.1700
Data Index: 4307588 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19