Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.5743. Min Act: -0.1700
Data Index: 6819695 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3868. Min Act: -0.1700
Data Index: 7468250 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3243. Min Act: -0.1700
Data Index: 1762844 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3243. Min Act: -0.1700
Data Index: 8117155 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3243. Min Act: -0.1700
Data Index: 8176589 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3868. Min Act: -0.1700
Data Index: 8723810 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3243. Min Act: -0.1700
Data Index: 1989048 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.3243. Min Act: -0.1700
Data Index: 4263578 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.2618. Min Act: -0.1700
Data Index: 7253426 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1993. Min Act: -0.1700
Data Index: 7480474 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.2618. Min Act: -0.1700
Data Index: 1011422 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1993. Min Act: -0.1700
Data Index: 8753351 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1993. Min Act: -0.1700
Data Index: 5087254 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1368. Min Act: -0.1700
Data Index: 6798538 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1368. Min Act: -0.1700
Data Index: 2069259 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1368. Min Act: -0.1700
Data Index: 4662096 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1368. Min Act: -0.1700
Data Index: 594169 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1368. Min Act: -0.1700
Data Index: 7922362 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.1368. Min Act: -0.1700
Data Index: 471491 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5743. Min Range: -9.5743
Max Act: 9.0743. Min Act: -0.1700
Data Index: 4634201 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19