Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1222 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1643. Min Act: -0.1700
Data Index: 7517728 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1486. Min Act: -0.1700
Data Index: 8339516 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1171. Min Act: -0.1700
Data Index: 1253123 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1328. Min Act: -0.1700
Data Index: 6193480 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1013. Min Act: -0.1700
Data Index: 6921479 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1013. Min Act: -0.1700
Data Index: 7276537 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1013. Min Act: -0.1700
Data Index: 8324669 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1013. Min Act: -0.1700
Data Index: 8220100 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1013. Min Act: -0.1700
Data Index: 687879 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 6630277 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0698. Min Act: -0.1700
Data Index: 5679882 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 1118942 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 7217471 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 8003019 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 7224542 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 7690066 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 5741663 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 5052322 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0856. Min Act: -0.1700
Data Index: 8644691 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.0698. Min Act: -0.1700
Data Index: 5625560 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19