Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.8229. Min Act: -0.1700
Data Index: 7557635 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.6042. Min Act: -0.1700
Data Index: 1114548 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.6042. Min Act: -0.1700
Data Index: 7734652 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.4792. Min Act: -0.1700
Data Index: 6454969 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.1979. Min Act: -0.1700
Data Index: 4309797 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.2292. Min Act: -0.1700
Data Index: 820393 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.0104. Min Act: -0.1700
Data Index: 2687967 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.0417. Min Act: -0.1700
Data Index: 2258630 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.9792. Min Act: -0.1700
Data Index: 4067760 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.0104. Min Act: -0.1700
Data Index: 7231538 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.0104. Min Act: -0.1700
Data Index: 6545533 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8229. Min Range: -7.8229
Max Act: 7.0104. Min Act: -0.1700
Data Index: 7231543 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.9792. Min Act: -0.1700
Data Index: 4284860 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.9479. Min Act: -0.1700
Data Index: 3084749 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.9167. Min Act: -0.1700
Data Index: 1464834 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.9479. Min Act: -0.1700
Data Index: 7412150 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.9167. Min Act: -0.1700
Data Index: 4366308 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.8854. Min Act: -0.1700
Data Index: 7962458 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.8229. Min Act: -0.1700
Data Index: 3657515 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8229. Min Range: -7.8229
Max Act: 6.8229. Min Act: -0.1700
Data Index: 3511490 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19