Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.7786. Min Act: -0.1700
Data Index: 3006746 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.7786. Min Act: -0.1700
Data Index: 890906 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.7161. Min Act: -0.1696
Data Index: 8362344 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6536. Min Act: -0.1700
Data Index: 2423208 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6536. Min Act: -0.1697
Data Index: 15824 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6536. Min Act: -0.1700
Data Index: 3537547 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6224. Min Act: -0.1698
Data Index: 3977484 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6224. Min Act: -0.1700
Data Index: 3944630 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6224. Min Act: -0.1700
Data Index: 5087608 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6224. Min Act: -0.1692
Data Index: 1814057 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.6224. Min Act: -0.1700
Data Index: 6464241 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5911. Min Act: -0.1700
Data Index: 4145723 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5911. Min Act: -0.1700
Data Index: 1785328 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1700
Data Index: 7568754 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1700
Data Index: 6567071 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1700
Data Index: 3618623 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1700
Data Index: 1445151 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1699
Data Index: 184115 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1700
Data Index: 364912 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7786. Min Range: -4.7786
Max Act: 4.5599. Min Act: -0.1700
Data Index: 1202063 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19