Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 379 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.8861. Min Act: -0.1700
Data Index: 6317654 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.8549. Min Act: -0.1700
Data Index: 4772493 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.8236. Min Act: -0.1700
Data Index: 8090885 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7924. Min Act: -0.1700
Data Index: 1972574 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7611. Min Act: -0.1700
Data Index: 1972575 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7299. Min Act: -0.1700
Data Index: 6014686 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7299. Min Act: -0.1700
Data Index: 608473 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7299. Min Act: -0.1700
Data Index: 1528143 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6986. Min Act: -0.1700
Data Index: 4860624 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 5995591 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 249626 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 1786908 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 8601660 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 5977674 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 5101382 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 1427151 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 5976516 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 358474 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 5977672 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 2311282 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19