Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1695. Min Range: -8.1695
Max Act: 8.1695. Min Act: -0.1700
Data Index: 880300 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.9195. Min Act: -0.1700
Data Index: 3647337 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.7945. Min Act: -0.1700
Data Index: 5894867 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.7320. Min Act: -0.1700
Data Index: 2793517 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.7320. Min Act: -0.1700
Data Index: 5112651 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.6695. Min Act: -0.1700
Data Index: 7008835 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.6695. Min Act: -0.1700
Data Index: 7688016 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5758. Min Act: -0.1700
Data Index: 8714000 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5758. Min Act: -0.1700
Data Index: 4302250 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5445. Min Act: -0.1700
Data Index: 2920175 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5133. Min Act: -0.1700
Data Index: 6500799 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5445. Min Act: -0.1700
Data Index: 5349147 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5445. Min Act: -0.1700
Data Index: 8089997 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5133. Min Act: -0.1700
Data Index: 3470691 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.5133. Min Act: -0.1700
Data Index: 6323434 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.4820. Min Act: -0.1700
Data Index: 1544854 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.4820. Min Act: -0.1700
Data Index: 6875462 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.4820. Min Act: -0.1700
Data Index: 3176291 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.4820. Min Act: -0.1700
Data Index: 4213039 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1695. Min Range: -8.1695
Max Act: 7.4508. Min Act: -0.1700
Data Index: 2660149 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19