Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0958. Min Act: -0.1672
Data Index: 7178225 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0695. Min Act: -0.1692
Data Index: 6073176 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0608. Min Act: -0.1650
Data Index: 5087417 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0608. Min Act: -0.1672
Data Index: 8417935 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0608. Min Act: -0.1692
Data Index: 6233073 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0521. Min Act: -0.1653
Data Index: 2985082 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0434. Min Act: -0.1504
Data Index: 6986856 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0521. Min Act: -0.1644
Data Index: 1534085 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0521. Min Act: -0.1700
Data Index: 984632 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0434. Min Act: -0.1692
Data Index: 6519409 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0434. Min Act: -0.1577
Data Index: 3128035 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0434. Min Act: -0.1661
Data Index: 1893496 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1700
Data Index: 3876948 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1700
Data Index: 7863996 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1691
Data Index: 5861658 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1647
Data Index: 5118916 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1690
Data Index: 2074422 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1700
Data Index: 1827258 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0259. Min Act: -0.1700
Data Index: 3550534 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0958. Min Range: -1.0958
Max Act: 1.0347. Min Act: -0.1524
Data Index: 1790094 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19