Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4067 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.3081. Min Act: -0.1698
Data Index: 2619164 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2816. Min Act: -0.1603
Data Index: 8808769 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2640. Min Act: -0.1393
Data Index: 8385329 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2551. Min Act: -0.1321
Data Index: 4339685 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2463. Min Act: -0.1700
Data Index: 2992813 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2463. Min Act: -0.1669
Data Index: 1110097 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2375. Min Act: -0.1700
Data Index: 1695283 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2287. Min Act: -0.1689
Data Index: 2563724 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2111. Min Act: -0.1700
Data Index: 8714095 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2111. Min Act: -0.1695
Data Index: 3604885 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2199. Min Act: -0.1700
Data Index: 3401574 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2023. Min Act: -0.1699
Data Index: 8171454 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2111. Min Act: -0.1700
Data Index: 6633740 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2199. Min Act: -0.1700
Data Index: 8794053 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2111. Min Act: -0.1700
Data Index: 1880648 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2111. Min Act: -0.1652
Data Index: 7701083 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2023. Min Act: -0.1700
Data Index: 3219162 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2023. Min Act: -0.1700
Data Index: 7642789 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2023. Min Act: -0.1700
Data Index: 260815 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3081. Min Range: -1.3081
Max Act: 1.2023. Min Act: -0.1691
Data Index: 5620272 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19