Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3418. Min Act: -0.1700
Data Index: 635504 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3506. Min Act: -0.1700
Data Index: 1380927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3330. Min Act: -0.1700
Data Index: 7347034 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3242. Min Act: -0.1678
Data Index: 6943624 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3154. Min Act: -0.1638
Data Index: 7514393 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3154. Min Act: -0.1699
Data Index: 3884821 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3065. Min Act: -0.1690
Data Index: 4858801 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3154. Min Act: -0.1700
Data Index: 5591290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.3065. Min Act: -0.1700
Data Index: 2997694 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1670
Data Index: 8680298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1699
Data Index: 2248888 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2801. Min Act: -0.1700
Data Index: 7321076 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2889. Min Act: -0.1691
Data Index: 4377922 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2977. Min Act: -0.1681
Data Index: 1942446 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2801. Min Act: -0.1693
Data Index: 283991 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2801. Min Act: -0.1693
Data Index: 352361 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2713. Min Act: -0.1694
Data Index: 7011807 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2624. Min Act: -0.1700
Data Index: 2602547 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2713. Min Act: -0.1698
Data Index: 6769062 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3506. Min Range: -1.3506
Max Act: 1.2801. Min Act: -0.1681
Data Index: 2671055 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19