Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.1044. Min Act: -0.1700
Data Index: 4884056 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.1517. Min Act: -0.1700
Data Index: 2938203 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.1044. Min Act: -0.1700
Data Index: 3835397 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.0729. Min Act: -0.1700
Data Index: 1188791 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.0413. Min Act: -0.1700
Data Index: 3232803 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.0413. Min Act: -0.1700
Data Index: 1602947 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.0413. Min Act: -0.1700
Data Index: 1941564 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.0571. Min Act: -0.1700
Data Index: 1613422 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1517. Min Range: -3.1517
Max Act: 3.0255. Min Act: -0.1700
Data Index: 1009982 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9939. Min Act: -0.1700
Data Index: 1072543 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9781. Min Act: -0.1700
Data Index: 7142111 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9939. Min Act: -0.1700
Data Index: 4504673 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9623. Min Act: -0.1700
Data Index: 6995928 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9781. Min Act: -0.1700
Data Index: 6911936 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9623. Min Act: -0.1700
Data Index: 132830 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9623. Min Act: -0.1700
Data Index: 5475242 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9465. Min Act: -0.1700
Data Index: 4377806 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9623. Min Act: -0.1700
Data Index: 6279855 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9623. Min Act: -0.1700
Data Index: 5727125 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1517. Min Range: -3.1517
Max Act: 2.9623. Min Act: -0.1700
Data Index: 1982716 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19