Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4351 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4841. Min Act: -0.1700
Data Index: 2078424 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4619. Min Act: -0.1699
Data Index: 1776803 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4255. Min Act: -0.1694
Data Index: 1339348 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4255. Min Act: -0.1682
Data Index: 4935426 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4255. Min Act: -0.1700
Data Index: 6111469 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4184. Min Act: -0.1697
Data Index: 7120656 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4041. Min Act: -0.1691
Data Index: 7664517 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4041. Min Act: -0.1676
Data Index: 6056273 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.4041. Min Act: -0.1686
Data Index: 6725465 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3971. Min Act: -0.1692
Data Index: 969224 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3971. Min Act: -0.1698
Data Index: 1820765 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3901. Min Act: -0.1692
Data Index: 7120655 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3831. Min Act: -0.1698
Data Index: 205508 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3831. Min Act: -0.1700
Data Index: 487041 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3761. Min Act: -0.1696
Data Index: 1335533 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3761. Min Act: -0.1700
Data Index: 6369108 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3761. Min Act: -0.1699
Data Index: 2068742 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3831. Min Act: -0.1688
Data Index: 5437928 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3692. Min Act: -0.1700
Data Index: 1335544 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4841. Min Range: -0.4841
Max Act: 0.3623. Min Act: -0.1700
Data Index: 7052418 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19