Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1552 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.8689. Min Act: -0.1700
Data Index: 6310470 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.8064. Min Act: -0.1700
Data Index: 1541549 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.8064. Min Act: -0.1700
Data Index: 5570621 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.7439. Min Act: -0.1700
Data Index: 7089753 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.7439. Min Act: -0.1700
Data Index: 1555330 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.6814. Min Act: -0.1700
Data Index: 4809040 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.6189. Min Act: -0.1700
Data Index: 3019732 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.6814. Min Act: -0.1700
Data Index: 2564335 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.5564. Min Act: -0.1700
Data Index: 2161915 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.5564. Min Act: -0.1700
Data Index: 4713705 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.4939. Min Act: -0.1700
Data Index: 3885509 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.4314. Min Act: -0.1700
Data Index: 7527968 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.3689. Min Act: -0.1700
Data Index: 5129791 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.3064. Min Act: -0.1700
Data Index: 2173888 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.2439. Min Act: -0.1700
Data Index: 7005497 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.3064. Min Act: -0.1700
Data Index: 8815889 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.3064. Min Act: -0.1700
Data Index: 3695499 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.2439. Min Act: -0.1700
Data Index: 3598013 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.1814. Min Act: -0.1700
Data Index: 2536857 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8689. Min Range: -8.8689
Max Act: 8.1814. Min Act: -0.1700
Data Index: 6336140 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19