Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.7639. Min Act: -0.1700
Data Index: 3771915 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.7639. Min Act: -0.1700
Data Index: 8664348 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.7000. Min Act: -0.1700
Data Index: 6765598 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6839. Min Act: -0.1700
Data Index: 2337812 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6839. Min Act: -0.1700
Data Index: 4945602 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6839. Min Act: -0.1700
Data Index: 1611680 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6839. Min Act: -0.1700
Data Index: 8639850 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6519. Min Act: -0.1700
Data Index: 7097441 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6839. Min Act: -0.1700
Data Index: 1616340 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6519. Min Act: -0.1700
Data Index: 7474724 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6519. Min Act: -0.1700
Data Index: 1616341 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6358. Min Act: -0.1700
Data Index: 3133714 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6358. Min Act: -0.1700
Data Index: 7950159 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6198. Min Act: -0.1700
Data Index: 105201 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6037. Min Act: -0.1700
Data Index: 6195049 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6358. Min Act: -0.1700
Data Index: 1619203 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6198. Min Act: -0.1700
Data Index: 1220880 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6198. Min Act: -0.1700
Data Index: 603482 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6358. Min Act: -0.1700
Data Index: 8605764 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7639. Min Range: -2.7639
Max Act: 2.6198. Min Act: -0.1700
Data Index: 3345092 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19