Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 360 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6527. Min Act: -0.1700
Data Index: 1870776 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6178. Min Act: -0.1699
Data Index: 1965820 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6353. Min Act: -0.1700
Data Index: 3690576 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6178. Min Act: -0.1692
Data Index: 5560952 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6004. Min Act: -0.1700
Data Index: 6410318 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6178. Min Act: -0.1700
Data Index: 5792711 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5829. Min Act: -0.1697
Data Index: 384420 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5742. Min Act: -0.1699
Data Index: 6775311 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5829. Min Act: -0.1700
Data Index: 5338476 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5829. Min Act: -0.1700
Data Index: 3924396 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.6004. Min Act: -0.1497
Data Index: 2681574 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5829. Min Act: -0.1698
Data Index: 5447685 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5829. Min Act: -0.1586
Data Index: 2681556 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5742. Min Act: -0.1528
Data Index: 2681566 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5654. Min Act: -0.1700
Data Index: 1508452 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5829. Min Act: -0.1530
Data Index: 2681573 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5654. Min Act: -0.1589
Data Index: 2681562 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5654. Min Act: -0.1700
Data Index: 6152001 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5654. Min Act: -0.1453
Data Index: 2681580 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6527. Min Range: -1.6527
Max Act: 1.5654. Min Act: -0.1685
Data Index: 6139358 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19