Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0988. Min Range: -8.0988
Max Act: 8.0988. Min Act: -0.1700
Data Index: 8635687 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.7863. Min Act: -0.1700
Data Index: 1221226 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.6613. Min Act: -0.1700
Data Index: 7767690 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.5988. Min Act: -0.1700
Data Index: 6674681 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.5363. Min Act: -0.1700
Data Index: 4303344 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.4738. Min Act: -0.1700
Data Index: 3860687 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.4113. Min Act: -0.1700
Data Index: 7816762 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3488. Min Act: -0.1700
Data Index: 5387776 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3488. Min Act: -0.1700
Data Index: 731666 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3488. Min Act: -0.1700
Data Index: 1221227 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.4113. Min Act: -0.1700
Data Index: 932815 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.4113. Min Act: -0.1700
Data Index: 7846423 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3488. Min Act: -0.1700
Data Index: 2097986 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3488. Min Act: -0.1700
Data Index: 8681175 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3176. Min Act: -0.1700
Data Index: 5920485 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.3176. Min Act: -0.1700
Data Index: 4374714 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.2551. Min Act: -0.1700
Data Index: 3565893 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.2863. Min Act: -0.1700
Data Index: 4066362 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.2863. Min Act: -0.1700
Data Index: 7969762 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0988. Min Range: -8.0988
Max Act: 7.2238. Min Act: -0.1700
Data Index: 8266862 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19