Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.9461. Min Act: -0.1700
Data Index: 1574015 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.7274. Min Act: -0.1700
Data Index: 4024894 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.6961. Min Act: -0.1700
Data Index: 4841963 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.6649. Min Act: -0.1700
Data Index: 6607066 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.6336. Min Act: -0.1700
Data Index: 713391 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.6336. Min Act: -0.1700
Data Index: 1631132 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.5399. Min Act: -0.1700
Data Index: 5747794 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.5399. Min Act: -0.1700
Data Index: 339741 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.5399. Min Act: -0.1700
Data Index: 4121150 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.5399. Min Act: -0.1700
Data Index: 6842471 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.4774. Min Act: -0.1700
Data Index: 1590902 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.5086. Min Act: -0.1700
Data Index: 4850592 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.4774. Min Act: -0.1700
Data Index: 2479742 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.4461. Min Act: -0.1700
Data Index: 6897059 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.3836. Min Act: -0.1700
Data Index: 7192598 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.3836. Min Act: -0.1700
Data Index: 2968981 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.3836. Min Act: -0.1700
Data Index: 8732085 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.3211. Min Act: -0.1700
Data Index: 5293325 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.3524. Min Act: -0.1700
Data Index: 8302428 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9461. Min Range: -6.9461
Max Act: 6.3524. Min Act: -0.1700
Data Index: 660290 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19