Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.6477. Min Act: -0.1700
Data Index: 4169143 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.3977. Min Act: -0.1700
Data Index: 1416839 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.3352. Min Act: -0.1700
Data Index: 3722618 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.2727. Min Act: -0.1700
Data Index: 2122539 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.2727. Min Act: -0.1700
Data Index: 8303740 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.2102. Min Act: -0.1700
Data Index: 5869437 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.1789. Min Act: -0.1700
Data Index: 7977756 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.1477. Min Act: -0.1700
Data Index: 7894425 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.1477. Min Act: -0.1700
Data Index: 4219022 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.0227. Min Act: -0.1700
Data Index: 631644 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.9914. Min Act: -0.1700
Data Index: 4613530 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6477. Min Range: -7.6477
Max Act: 7.0227. Min Act: -0.1700
Data Index: 6750951 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.9602. Min Act: -0.1700
Data Index: 142945 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.9602. Min Act: -0.1700
Data Index: 3372759 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.9602. Min Act: -0.1700
Data Index: 1084709 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.8977. Min Act: -0.1700
Data Index: 8249435 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.8664. Min Act: -0.1700
Data Index: 5381552 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.8664. Min Act: -0.1700
Data Index: 7143630 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.8352. Min Act: -0.1700
Data Index: 2852758 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6477. Min Range: -7.6477
Max Act: 6.8352. Min Act: -0.1700
Data Index: 4812283 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19