Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.5486. Min Act: -0.1700
Data Index: 2520015 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.4548. Min Act: -0.1646
Data Index: 1502370 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.3923. Min Act: -0.1700
Data Index: 7134860 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.2673. Min Act: -0.1700
Data Index: 4454234 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.1736. Min Act: -0.1700
Data Index: 1502367 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.1423. Min Act: -0.1700
Data Index: 1455486 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.1423. Min Act: -0.1698
Data Index: 6601627 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.1111. Min Act: -0.1690
Data Index: 6601626 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.0486. Min Act: -0.1700
Data Index: 607459 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5486. Min Range: -6.5486
Max Act: 6.0173. Min Act: -0.1700
Data Index: 3061264 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.9548. Min Act: -0.1700
Data Index: 4454235 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.9236. Min Act: -0.1424
Data Index: 8105039 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.9236. Min Act: -0.1673
Data Index: 261009 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.9548. Min Act: -0.1700
Data Index: 1137217 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.8923. Min Act: -0.1700
Data Index: 5837613 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.8923. Min Act: -0.1700
Data Index: 6421930 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.8923. Min Act: -0.1681
Data Index: 3210995 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.8298. Min Act: -0.1588
Data Index: 3240666 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.8611. Min Act: -0.1700
Data Index: 5029278 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5486. Min Range: -6.5486
Max Act: 5.8298. Min Act: -0.1700
Data Index: 6903548 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19