Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1432. Min Range: -8.1432
Max Act: 8.1432. Min Act: -0.1700
Data Index: 6160297 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1432. Min Range: -8.1432
Max Act: 8.0182. Min Act: -0.1697
Data Index: 52340 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.9557. Min Act: -0.1700
Data Index: 11507 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.9557. Min Act: -0.1700
Data Index: 4302283 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 593444 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 7754553 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 2302826 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 4062394 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 1324555 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 6014349 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 5840373 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 8382604 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8932. Min Act: -0.1700
Data Index: 7820184 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 5887586 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 1590802 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 2254174 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 2785860 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.8307. Min Act: -0.1700
Data Index: 2730061 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.7682. Min Act: -0.1700
Data Index: 1026757 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1432. Min Range: -8.1432
Max Act: 7.7057. Min Act: -0.1700
Data Index: 1508347 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19