Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2072 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5329. Min Range: -4.5329
Max Act: 4.5329. Min Act: -0.1700
Data Index: 4286383 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5329. Min Range: -4.5329
Max Act: 4.1266. Min Act: -0.1700
Data Index: 2485080 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5329. Min Range: -4.5329
Max Act: 4.0329. Min Act: -0.1700
Data Index: 7444732 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5329. Min Range: -4.5329
Max Act: 4.0329. Min Act: -0.1700
Data Index: 2195222 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5329. Min Range: -4.5329
Max Act: 4.0329. Min Act: -0.1700
Data Index: 5498945 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5329. Min Range: -4.5329
Max Act: 4.0016. Min Act: -0.1700
Data Index: 6010731 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9703. Min Act: -0.1700
Data Index: 8205776 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9391. Min Act: -0.1700
Data Index: 7978164 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9703. Min Act: -0.1700
Data Index: 5688249 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9391. Min Act: -0.1700
Data Index: 5728050 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9703. Min Act: -0.1700
Data Index: 4792419 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9703. Min Act: -0.1700
Data Index: 2168179 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9078. Min Act: -0.1700
Data Index: 4940211 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9391. Min Act: -0.1700
Data Index: 2693559 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9391. Min Act: -0.1700
Data Index: 1304558 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.9078. Min Act: -0.1700
Data Index: 6373464 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.8765. Min Act: -0.1700
Data Index: 8202054 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.8765. Min Act: -0.1700
Data Index: 6956854 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.8765. Min Act: -0.1700
Data Index: 3438965 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5329. Min Range: -4.5329
Max Act: 3.8922. Min Act: -0.1700
Data Index: 273899 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19