Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.6976. Min Act: -0.1700
Data Index: 4136319 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.4476. Min Act: -0.1700
Data Index: 5380104 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.2601. Min Act: -0.1700
Data Index: 6593964 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.1976. Min Act: -0.1700
Data Index: 1933833 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.1351. Min Act: -0.1700
Data Index: 7476564 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.0726. Min Act: -0.1700
Data Index: 1032577 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.0726. Min Act: -0.1700
Data Index: 7543446 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6976. Min Range: -9.6976
Max Act: 9.0726. Min Act: -0.1700
Data Index: 3006171 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.9476. Min Act: -0.1700
Data Index: 5435772 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.6976. Min Act: -0.1700
Data Index: 6369963 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.6976. Min Act: -0.1700
Data Index: 1674480 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.6976. Min Act: -0.1700
Data Index: 559357 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 2734279 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.6351. Min Act: -0.1700
Data Index: 7473272 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.6351. Min Act: -0.1700
Data Index: 761502 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 4626 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 2505960 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 4947504 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 662212 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6976. Min Range: -9.6976
Max Act: 8.5726. Min Act: -0.1700
Data Index: 4188826 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19