Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1429. Min Range: -4.1429
Max Act: 4.1429. Min Act: -0.1700
Data Index: 691276 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1429. Min Range: -4.1429
Max Act: 4.1116. Min Act: -0.1700
Data Index: 3933033 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1429. Min Range: -4.1429
Max Act: 4.0804. Min Act: -0.1700
Data Index: 2529432 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9866. Min Act: -0.1700
Data Index: 5350700 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9553. Min Act: -0.1700
Data Index: 5230239 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9241. Min Act: -0.1700
Data Index: 3946212 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.9553. Min Act: -0.1700
Data Index: 1901728 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 4464984 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 7565800 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8303. Min Act: -0.1700
Data Index: 470350 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8303. Min Act: -0.1700
Data Index: 6116412 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 7082776 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.7990. Min Act: -0.1700
Data Index: 5690739 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8615. Min Act: -0.1700
Data Index: 3860280 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.8303. Min Act: -0.1700
Data Index: 1951293 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.7990. Min Act: -0.1700
Data Index: 3987246 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.7990. Min Act: -0.1700
Data Index: 2234656 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.7834. Min Act: -0.1700
Data Index: 391882 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.7834. Min Act: -0.1700
Data Index: 2467031 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1429. Min Range: -4.1429
Max Act: 3.7834. Min Act: -0.1700
Data Index: 1619 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19