Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0510. Min Range: -6.0510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 4405326 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.8323. Min Act: -0.1700
Data Index: 6033492 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.8010. Min Act: -0.1700
Data Index: 3719510 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.7073. Min Act: -0.1700
Data Index: 329691 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.7073. Min Act: -0.1700
Data Index: 7207177 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6448. Min Act: -0.1700
Data Index: 3719511 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6448. Min Act: -0.1700
Data Index: 329692 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.6135. Min Act: -0.1700
Data Index: 329693 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5510. Min Act: -0.1700
Data Index: 5475659 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5198. Min Act: -0.1700
Data Index: 7239520 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5198. Min Act: -0.1700
Data Index: 329694 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.5198. Min Act: -0.1700
Data Index: 786182 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4885. Min Act: -0.1700
Data Index: 4501335 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4573. Min Act: -0.1700
Data Index: 6033495 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4260. Min Act: -0.1700
Data Index: 3735328 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.3948. Min Act: -0.1700
Data Index: 3115240 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.4260. Min Act: -0.1700
Data Index: 36424 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.3948. Min Act: -0.1700
Data Index: 5133581 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.3948. Min Act: -0.1700
Data Index: 6033496 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0510. Min Range: -6.0510
Max Act: 5.3948. Min Act: -0.1700
Data Index: 1920896 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19