Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1541. Min Range: -7.1541
Max Act: 7.1541. Min Act: -0.1700
Data Index: 8112734 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.9666. Min Act: -0.1700
Data Index: 8035908 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.9353. Min Act: -0.1700
Data Index: 1658073 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.9041. Min Act: -0.1700
Data Index: 2126937 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.9041. Min Act: -0.1700
Data Index: 517944 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5981546 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.9041. Min Act: -0.1700
Data Index: 131918 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8728. Min Act: -0.1700
Data Index: 6796276 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8728. Min Act: -0.1700
Data Index: 4177436 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8416. Min Act: -0.1700
Data Index: 1318150 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8728. Min Act: -0.1700
Data Index: 4515075 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8103. Min Act: -0.1700
Data Index: 730971 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8103. Min Act: -0.1700
Data Index: 7599615 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.8103. Min Act: -0.1700
Data Index: 107867 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.7791. Min Act: -0.1700
Data Index: 1519659 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.7791. Min Act: -0.1700
Data Index: 7204319 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.7478. Min Act: -0.1700
Data Index: 3052652 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.7166. Min Act: -0.1700
Data Index: 3041786 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.7478. Min Act: -0.1700
Data Index: 2757595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1541. Min Range: -7.1541
Max Act: 6.7166. Min Act: -0.1700
Data Index: 2822337 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19