Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5747. Min Act: -0.0708
Data Index: 5928114 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5309. Min Act: 0.0137
Data Index: 7857582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5309. Min Act: 0.0137
Data Index: 7857580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5309. Min Act: -0.1368
Data Index: 8088462 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5046. Min Act: 0.0293
Data Index: 3224036 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.5046. Min Act: -0.0517
Data Index: 5738535 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4694. Min Act: -0.1028
Data Index: 3224739 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4518. Min Act: -0.1522
Data Index: 6060687 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4430. Min Act: -0.1368
Data Index: 4921722 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4518. Min Act: -0.1516
Data Index: 5933979 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4078. Min Act: -0.1392
Data Index: 3849758 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4254. Min Act: -0.1635
Data Index: 3342178 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4078. Min Act: -0.1311
Data Index: 3975202 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4166. Min Act: -0.1107
Data Index: 3883819 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.4078. Min Act: -0.1085
Data Index: 1808982 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3990. Min Act: -0.1085
Data Index: 1753333 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3990. Min Act: -0.1336
Data Index: 4008817 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3990. Min Act: -0.1614
Data Index: 3221105 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3990. Min Act: 0.0995
Data Index: 2173418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5747. Min Range: -1.5747
Max Act: 1.3902. Min Act: -0.0693
Data Index: 5206641 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19