Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2292 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.6922. Min Act: -0.1700
Data Index: 5769668 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5615. Min Act: -0.1696
Data Index: 1676776 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5440. Min Act: -0.1700
Data Index: 4146709 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5352. Min Act: -0.1700
Data Index: 611013 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5264. Min Act: -0.1700
Data Index: 3735508 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5089. Min Act: -0.1700
Data Index: 4712339 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5177. Min Act: -0.1700
Data Index: 8724541 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5177. Min Act: -0.1700
Data Index: 4496246 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5089. Min Act: -0.1700
Data Index: 4725626 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5089. Min Act: -0.1700
Data Index: 427917 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.5001. Min Act: -0.1700
Data Index: 7603803 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4913. Min Act: -0.1700
Data Index: 1273945 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4913. Min Act: -0.1700
Data Index: 3883062 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4825. Min Act: -0.1700
Data Index: 674681 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4913. Min Act: -0.1700
Data Index: 6433983 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4913. Min Act: -0.1700
Data Index: 5352140 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4825. Min Act: -0.1700
Data Index: 5694722 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4738. Min Act: -0.1700
Data Index: 3164652 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4825. Min Act: -0.1699
Data Index: 2283860 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6922. Min Range: -1.6922
Max Act: 1.4825. Min Act: -0.1700
Data Index: 3776969 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19