Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.9528. Min Act: -0.1700
Data Index: 8814848 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.8903. Min Act: -0.1700
Data Index: 5798922 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.8591. Min Act: -0.1700
Data Index: 596001 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.8278. Min Act: -0.1700
Data Index: 6561849 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 3564600 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.7653. Min Act: -0.1700
Data Index: 4793566 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.6716. Min Act: -0.1700
Data Index: 1771413 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.6716. Min Act: -0.1700
Data Index: 8106081 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.6716. Min Act: -0.1700
Data Index: 1738550 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.7028. Min Act: -0.1700
Data Index: 2305738 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.6403. Min Act: -0.1700
Data Index: 5754691 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.6403. Min Act: -0.1700
Data Index: 6440440 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5778. Min Act: -0.1700
Data Index: 6982041 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5778. Min Act: -0.1700
Data Index: 1210252 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5778. Min Act: -0.1700
Data Index: 5402580 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5778. Min Act: -0.1700
Data Index: 3096573 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5466. Min Act: -0.1700
Data Index: 425545 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5466. Min Act: -0.1700
Data Index: 7342801 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5466. Min Act: -0.1700
Data Index: 3146178 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9528. Min Range: -4.9528
Max Act: 4.5466. Min Act: -0.1700
Data Index: 5640415 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19