Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.7308. Min Act: -0.1597
Data Index: 5996462 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.6614. Min Act: -0.1700
Data Index: 5996463 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.6266. Min Act: -0.1700
Data Index: 6685197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.6179. Min Act: -0.1700
Data Index: 3975923 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.6004. Min Act: -0.1660
Data Index: 1031128 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.6004. Min Act: -0.1469
Data Index: 980649 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5917. Min Act: -0.1700
Data Index: 4873430 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5742. Min Act: -0.1685
Data Index: 5742233 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5742. Min Act: -0.1700
Data Index: 4729451 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5742. Min Act: -0.1700
Data Index: 8044131 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5742. Min Act: -0.1700
Data Index: 8107853 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5654. Min Act: -0.1700
Data Index: 5333590 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5567. Min Act: -0.1699
Data Index: 8787481 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5654. Min Act: -0.1700
Data Index: 4587176 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5654. Min Act: -0.1669
Data Index: 6897717 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5567. Min Act: -0.1700
Data Index: 2184010 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5567. Min Act: -0.1700
Data Index: 8461152 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5567. Min Act: -0.1699
Data Index: 1773555 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5567. Min Act: -0.1683
Data Index: 4240861 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7308. Min Range: -1.7308
Max Act: 1.5567. Min Act: -0.1700
Data Index: 5901897 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19