Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2282. Min Range: -8.2282
Max Act: 8.2282. Min Act: -0.1700
Data Index: 639154 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2282. Min Range: -8.2282
Max Act: 8.1657. Min Act: -0.1700
Data Index: 260211 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2282. Min Range: -8.2282
Max Act: 8.1032. Min Act: -0.1700
Data Index: 3936407 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.8844. Min Act: -0.1700
Data Index: 2381019 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.8844. Min Act: -0.1700
Data Index: 7693771 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.8532. Min Act: -0.1700
Data Index: 3246809 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.8844. Min Act: -0.1700
Data Index: 1036170 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.8219. Min Act: -0.1700
Data Index: 1353181 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.7907. Min Act: -0.1700
Data Index: 5295017 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.8532. Min Act: -0.1700
Data Index: 2381018 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.7594. Min Act: -0.1700
Data Index: 1999013 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.7282. Min Act: -0.1700
Data Index: 6130405 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.7282. Min Act: -0.1700
Data Index: 8708429 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6969. Min Act: -0.1700
Data Index: 8708735 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6969. Min Act: -0.1700
Data Index: 7543039 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6657. Min Act: -0.1700
Data Index: 6743919 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6344. Min Act: -0.1700
Data Index: 1245459 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6032. Min Act: -0.1700
Data Index: 2803555 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6032. Min Act: -0.1700
Data Index: 7064389 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2282. Min Range: -8.2282
Max Act: 7.6032. Min Act: -0.1700
Data Index: 395441 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19