Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.2666. Min Act: -0.1700
Data Index: 1109373 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.1729. Min Act: -0.1700
Data Index: 508532 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.1416. Min Act: -0.1700
Data Index: 2454272 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.1729. Min Act: -0.1700
Data Index: 4331924 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.1416. Min Act: -0.1700
Data Index: 3654602 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.1104. Min Act: -0.1700
Data Index: 6913336 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 7328848 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 6907701 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0791. Min Act: -0.1700
Data Index: 4867509 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3848972 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 5632365 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3736189 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 7849741 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0166. Min Act: -0.1700
Data Index: 1934711 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0479. Min Act: -0.1700
Data Index: 519267 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0166. Min Act: -0.1700
Data Index: 532768 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7422951 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2666. Min Range: -5.2666
Max Act: 5.0166. Min Act: -0.1700
Data Index: 6424954 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2666. Min Range: -5.2666
Max Act: 4.9854. Min Act: -0.1700
Data Index: 385993 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2666. Min Range: -5.2666
Max Act: 4.9854. Min Act: -0.1700
Data Index: 4946524 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19