Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.8167. Min Act: -0.1700
Data Index: 6840981 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.8479. Min Act: -0.1700
Data Index: 2674118 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.8479. Min Act: -0.1700
Data Index: 769332 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.8167. Min Act: -0.1700
Data Index: 6463041 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.7228. Min Act: -0.1700
Data Index: 4443585 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6916. Min Act: -0.1700
Data Index: 6912789 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.7228. Min Act: -0.1700
Data Index: 7759323 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6603. Min Act: -0.1700
Data Index: 7857960 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6916. Min Act: -0.1700
Data Index: 7033940 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6916. Min Act: -0.1700
Data Index: 1351594 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6916. Min Act: -0.1700
Data Index: 5490878 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6603. Min Act: -0.1700
Data Index: 2588182 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6603. Min Act: -0.1700
Data Index: 8420275 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6603. Min Act: -0.1700
Data Index: 2001620 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6603. Min Act: -0.1700
Data Index: 8212099 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6290. Min Act: -0.1700
Data Index: 7099334 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6290. Min Act: -0.1700
Data Index: 1003472 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6290. Min Act: -0.1700
Data Index: 3726219 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6290. Min Act: -0.1700
Data Index: 2292002 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8479. Min Range: -3.8479
Max Act: 3.6290. Min Act: -0.1700
Data Index: 2821656 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19