Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1649. Min Range: -8.1649
Max Act: 8.1649. Min Act: -0.1700
Data Index: 1659691 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1649. Min Range: -8.1649
Max Act: 8.1024. Min Act: -0.1700
Data Index: 818710 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1649. Min Range: -8.1649
Max Act: 8.0399. Min Act: -0.1700
Data Index: 404922 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1649. Min Range: -8.1649
Max Act: 8.0399. Min Act: -0.1700
Data Index: 310047 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.9774. Min Act: -0.1700
Data Index: 4053729 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.9774. Min Act: -0.1700
Data Index: 8720119 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.8524. Min Act: -0.1700
Data Index: 3891674 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.8524. Min Act: -0.1700
Data Index: 4833398 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6649. Min Act: -0.1700
Data Index: 2050135 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.7274. Min Act: -0.1700
Data Index: 393284 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.7274. Min Act: -0.1700
Data Index: 5307214 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6649. Min Act: -0.1700
Data Index: 8237147 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6649. Min Act: -0.1700
Data Index: 8533286 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6024. Min Act: -0.1700
Data Index: 6776813 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6024. Min Act: -0.1700
Data Index: 1436737 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6024. Min Act: -0.1700
Data Index: 6332812 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.5399. Min Act: -0.1700
Data Index: 8010300 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6024. Min Act: -0.1700
Data Index: 1971161 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.5399. Min Act: -0.1700
Data Index: 287206 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1649. Min Range: -8.1649
Max Act: 7.6024. Min Act: -0.1700
Data Index: 7687507 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19