Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.6291. Min Act: -0.1699
Data Index: 1173926 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.6029. Min Act: -0.1693
Data Index: 1503058 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.6029. Min Act: -0.1700
Data Index: 3938561 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5942. Min Act: -0.1700
Data Index: 286131 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5767. Min Act: -0.1700
Data Index: 4593948 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5767. Min Act: -0.1700
Data Index: 6861254 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5854. Min Act: -0.1700
Data Index: 6999697 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5767. Min Act: -0.1700
Data Index: 7386083 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5680. Min Act: -0.1694
Data Index: 411312 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5592. Min Act: -0.1696
Data Index: 6648466 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5592. Min Act: -0.1691
Data Index: 1189402 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5505. Min Act: -0.1700
Data Index: 6983699 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5505. Min Act: -0.1691
Data Index: 5002392 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5417. Min Act: -0.1678
Data Index: 1951097 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5417. Min Act: -0.1692
Data Index: 5950417 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5505. Min Act: -0.1700
Data Index: 5627088 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5505. Min Act: -0.1700
Data Index: 6969551 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5417. Min Act: -0.1696
Data Index: 1647855 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5417. Min Act: -0.1687
Data Index: 1898275 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6291. Min Range: -1.6291
Max Act: 1.5329. Min Act: -0.1638
Data Index: 3937307 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19