Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1829. Min Range: -1.1829
Max Act: 1.1829. Min Act: -0.1700
Data Index: 4292781 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1829. Min Range: -1.1829
Max Act: 1.0514. Min Act: -0.1699
Data Index: 7934021 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1829. Min Range: -1.1829
Max Act: 1.0166. Min Act: -0.1698
Data Index: 8399402 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1829. Min Range: -1.1829
Max Act: 1.0079. Min Act: -0.1657
Data Index: 7949100 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9818. Min Act: -0.1695
Data Index: 461041 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9732. Min Act: -0.1700
Data Index: 872384 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9559. Min Act: -0.1695
Data Index: 1674325 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9559. Min Act: -0.1695
Data Index: 838825 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9645. Min Act: -0.1694
Data Index: 6911695 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9473. Min Act: -0.1700
Data Index: 3195184 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9301. Min Act: -0.1700
Data Index: 5837650 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9387. Min Act: -0.1700
Data Index: 6749663 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9387. Min Act: -0.1671
Data Index: 6843844 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9387. Min Act: -0.1695
Data Index: 2564743 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9301. Min Act: -0.1700
Data Index: 2292526 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9301. Min Act: -0.1671
Data Index: 88815 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9387. Min Act: -0.1700
Data Index: 2519545 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9215. Min Act: -0.1697
Data Index: 7539464 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9215. Min Act: -0.1700
Data Index: 838828 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1829. Min Range: -1.1829
Max Act: 0.9301. Min Act: -0.1690
Data Index: 3379657 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19