Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 4979785 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 5389625 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7915. Min Act: -0.1700
Data Index: 25411 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8217309 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 2973452 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4575043 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4001979 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 1483687 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6040. Min Act: -0.1700
Data Index: 4296203 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6040. Min Act: -0.1700
Data Index: 6301944 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 2053752 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5608473 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5674340 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5453092 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 7783471 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 25406 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 491652 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 7335643 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 6135797 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.5415. Min Act: -0.1700
Data Index: 1945233 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19