Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.5786. Min Act: -0.1681
Data Index: 199575 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.5698. Min Act: -0.1700
Data Index: 1294625 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.5523. Min Act: -0.1692
Data Index: 61797 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.5523. Min Act: -0.1700
Data Index: 2617860 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.5436. Min Act: -0.1700
Data Index: 6441542 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.5348. Min Act: -0.1700
Data Index: 2519664 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4997. Min Act: -0.1699
Data Index: 1060115 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4909. Min Act: -0.1700
Data Index: 8625511 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4997. Min Act: -0.1663
Data Index: 8748172 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4909. Min Act: -0.1700
Data Index: 7364115 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4909. Min Act: -0.1700
Data Index: 2292917 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4822. Min Act: -0.1700
Data Index: 250032 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4822. Min Act: -0.1700
Data Index: 1776938 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4734. Min Act: -0.1700
Data Index: 318621 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4734. Min Act: -0.1700
Data Index: 2764441 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4558. Min Act: -0.1700
Data Index: 1871338 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4646. Min Act: -0.1688
Data Index: 5824840 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4646. Min Act: -0.1700
Data Index: 3260736 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4646. Min Act: -0.1698
Data Index: 443578 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5786. Min Range: -1.5786
Max Act: 1.4558. Min Act: -0.1700
Data Index: 5036451 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19