Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3457. Min Range: -10.3457
Max Act: 10.3457. Min Act: -0.1700
Data Index: 145197 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.4082. Min Act: -0.1700
Data Index: 4388487 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.4082. Min Act: -0.1700
Data Index: 3457841 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.4082. Min Act: -0.1700
Data Index: 5258443 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.3457. Min Act: -0.1700
Data Index: 3865333 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.2207. Min Act: -0.1700
Data Index: 4471123 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.2207. Min Act: -0.1700
Data Index: 686571 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.1582. Min Act: -0.1700
Data Index: 3198787 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.1582. Min Act: -0.1700
Data Index: 1865521 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.1582. Min Act: -0.1700
Data Index: 2849393 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.0332. Min Act: -0.1700
Data Index: 3962203 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.0332. Min Act: -0.1700
Data Index: 635517 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.0332. Min Act: -0.1700
Data Index: 3270794 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.0332. Min Act: -0.1700
Data Index: 3603008 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3457. Min Range: -10.3457
Max Act: 8.9707. Min Act: -0.1700
Data Index: 2072417 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3457. Min Range: -10.3457
Max Act: 8.9707. Min Act: -0.1700
Data Index: 1434429 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3457. Min Range: -10.3457
Max Act: 9.0332. Min Act: -0.1700
Data Index: 3174590 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3457. Min Range: -10.3457
Max Act: 8.9707. Min Act: -0.1700
Data Index: 1180343 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3457. Min Range: -10.3457
Max Act: 8.9707. Min Act: -0.1700
Data Index: 2501547 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3457. Min Range: -10.3457
Max Act: 8.9707. Min Act: -0.1700
Data Index: 2881565 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19