Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 22.5507. Min Range: -22.5507
Max Act: 22.5507. Min Act: -0.1700
Data Index: 4332530 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 22.5507. Min Range: -22.5507
Max Act: 21.0507. Min Act: -0.1700
Data Index: 7299878 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 22.5507. Min Range: -22.5507
Max Act: 19.9257. Min Act: -0.1700
Data Index: 4420855 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 22.5507. Min Range: -22.5507
Max Act: 21.1757. Min Act: -0.1700
Data Index: 693544 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 22.5507. Min Range: -22.5507
Max Act: 20.9257. Min Act: -0.1700
Data Index: 55600 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 22.5507. Min Range: -22.5507
Max Act: 21.1757. Min Act: -0.1700
Data Index: 6364952 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 22.5507. Min Range: -22.5507
Max Act: 21.4257. Min Act: -0.1700
Data Index: 4316910 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 22.5507. Min Range: -22.5507
Max Act: 19.0507. Min Act: -0.1700
Data Index: 708724 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 22.5507. Min Range: -22.5507
Max Act: 21.3007. Min Act: -0.1700
Data Index: 6567536 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 22.5507. Min Range: -22.5507
Max Act: 20.6757. Min Act: -0.1700
Data Index: 7147105 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 22.5507. Min Range: -22.5507
Max Act: 16.3007. Min Act: -0.1700
Data Index: 6064439 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 22.5507. Min Range: -22.5507
Max Act: 21.0507. Min Act: -0.1700
Data Index: 3476534 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 22.5507. Min Range: -22.5507
Max Act: 18.8007. Min Act: -0.1700
Data Index: 137874 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 22.5507. Min Range: -22.5507
Max Act: 20.3007. Min Act: -0.1700
Data Index: 6957117 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 22.5507. Min Range: -22.5507
Max Act: 20.3007. Min Act: -0.1700
Data Index: 1582812 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 22.5507. Min Range: -22.5507
Max Act: 14.3007. Min Act: -0.1700
Data Index: 6078141 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 22.5507. Min Range: -22.5507
Max Act: 20.4257. Min Act: -0.1700
Data Index: 3864543 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 22.5507. Min Range: -22.5507
Max Act: 11.4257. Min Act: -0.1700
Data Index: 1649458 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 22.5507. Min Range: -22.5507
Max Act: 19.3007. Min Act: -0.1700
Data Index: 8151825 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 22.5507. Min Range: -22.5507
Max Act: 19.9257. Min Act: -0.1700
Data Index: 5584243 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19