Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5836 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.4763. Min Act: -0.1700
Data Index: 3473277 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.3826. Min Act: -0.1700
Data Index: 3447227 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.1013. Min Act: -0.1700
Data Index: 6552527 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.1013. Min Act: -0.1699
Data Index: 5561538 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.1326. Min Act: -0.1700
Data Index: 7033215 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0388. Min Act: -0.1700
Data Index: 677581 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0701. Min Act: -0.1700
Data Index: 3873216 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0388. Min Act: -0.1700
Data Index: 8548210 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0388. Min Act: -0.1700
Data Index: 2276639 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0388. Min Act: -0.1700
Data Index: 3353956 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0076. Min Act: -0.1700
Data Index: 4833266 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0388. Min Act: -0.1700
Data Index: 891882 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4763. Min Range: -5.4763
Max Act: 5.0076. Min Act: -0.1698
Data Index: 3412335 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9763. Min Act: -0.1700
Data Index: 8660103 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9451. Min Act: -0.1700
Data Index: 8750561 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9763. Min Act: -0.1700
Data Index: 8660100 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9763. Min Act: -0.1700
Data Index: 3885401 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9451. Min Act: -0.1700
Data Index: 7731784 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9451. Min Act: -0.1700
Data Index: 8531263 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4763. Min Range: -5.4763
Max Act: 4.9451. Min Act: -0.1700
Data Index: 3348303 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19