Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.7017. Min Act: -0.1700
Data Index: 780943 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.6060. Min Act: -0.1700
Data Index: 234141 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.6060. Min Act: -0.1700
Data Index: 4950965 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5885. Min Act: -0.1700
Data Index: 7502292 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5797. Min Act: -0.1700
Data Index: 1162421 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5623. Min Act: -0.1698
Data Index: 7679080 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5623. Min Act: -0.1697
Data Index: 6250457 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5535. Min Act: -0.1699
Data Index: 8695916 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5535. Min Act: -0.1699
Data Index: 6742545 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5447. Min Act: -0.1700
Data Index: 2053700 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5535. Min Act: -0.1698
Data Index: 7619185 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5535. Min Act: -0.1700
Data Index: 1603548 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5447. Min Act: -0.1698
Data Index: 7039446 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5447. Min Act: -0.1700
Data Index: 1187489 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5272. Min Act: -0.1700
Data Index: 3864116 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5272. Min Act: -0.1700
Data Index: 1613490 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5360. Min Act: -0.1692
Data Index: 4603784 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5447. Min Act: -0.1700
Data Index: 157081 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5360. Min Act: -0.1698
Data Index: 1033318 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7017. Min Range: -1.7017
Max Act: 1.5272. Min Act: -0.1598
Data Index: 6710215 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19