Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.8103. Min Act: -0.1700
Data Index: 4843867 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.7790. Min Act: -0.1700
Data Index: 8395066 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.7321. Min Act: -0.1700
Data Index: 1843688 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.7164. Min Act: -0.1700
Data Index: 747071 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.7008. Min Act: -0.1700
Data Index: 6825697 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6695. Min Act: -0.1700
Data Index: 4611593 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6539. Min Act: -0.1700
Data Index: 4615594 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6382. Min Act: -0.1700
Data Index: 4370834 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6539. Min Act: -0.1700
Data Index: 4760972 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6226. Min Act: -0.1700
Data Index: 7421927 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6069. Min Act: -0.1700
Data Index: 2194730 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6069. Min Act: -0.1700
Data Index: 3782832 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.6069. Min Act: -0.1700
Data Index: 2103583 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5913. Min Act: -0.1700
Data Index: 1224334 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5913. Min Act: -0.1700
Data Index: 1820829 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5756. Min Act: -0.1700
Data Index: 1470950 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5756. Min Act: -0.1700
Data Index: 3417726 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5600. Min Act: -0.1700
Data Index: 6113529 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5600. Min Act: -0.1700
Data Index: 3290288 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8103. Min Range: -3.8103
Max Act: 3.5600. Min Act: -0.1700
Data Index: 1517225 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19