Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 177 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.5008. Min Act: -0.1695
Data Index: 6292589 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4920. Min Act: -0.1700
Data Index: 2095455 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4745. Min Act: -0.1643
Data Index: 4989548 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4657. Min Act: -0.1686
Data Index: 8232339 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4657. Min Act: -0.1648
Data Index: 7132312 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4832. Min Act: -0.1699
Data Index: 1918634 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4657. Min Act: -0.1691
Data Index: 145888 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4745. Min Act: -0.1630
Data Index: 3851307 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4657. Min Act: -0.1700
Data Index: 2335669 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4657. Min Act: -0.1639
Data Index: 7472468 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4569. Min Act: -0.1697
Data Index: 5355285 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4481. Min Act: -0.1700
Data Index: 1409021 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4569. Min Act: -0.1630
Data Index: 2832984 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4305. Min Act: -0.1598
Data Index: 1279667 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4393. Min Act: -0.1684
Data Index: 478198 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4393. Min Act: -0.1639
Data Index: 712263 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4393. Min Act: -0.1655
Data Index: 6000947 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4481. Min Act: -0.1694
Data Index: 2698903 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4393. Min Act: -0.1698
Data Index: 3485725 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5008. Min Range: -1.5008
Max Act: 1.4393. Min Act: -0.1697
Data Index: 535082 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19