Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.6088. Min Act: -0.1700
Data Index: 757525 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.6088. Min Act: -0.1700
Data Index: 6929628 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.5776. Min Act: -0.1700
Data Index: 4628493 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.5151. Min Act: -0.1700
Data Index: 3269910 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.3901. Min Act: -0.1700
Data Index: 8139566 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.3588. Min Act: -0.1700
Data Index: 5870714 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.2963. Min Act: -0.1700
Data Index: 4557401 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.2651. Min Act: -0.1700
Data Index: 4695609 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.2338. Min Act: -0.1700
Data Index: 6328773 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 8693283 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 3237520 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.2026. Min Act: -0.1700
Data Index: 8364699 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.2026. Min Act: -0.1700
Data Index: 5953707 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 8511724 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.2026. Min Act: -0.1700
Data Index: 621159 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 7806959 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 3027648 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 2816719 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1713. Min Act: -0.1700
Data Index: 8429537 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6088. Min Range: -6.6088
Max Act: 6.1401. Min Act: -0.1700
Data Index: 937793 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19