Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0359. Min Range: -8.0359
Max Act: 8.0359. Min Act: -0.1700
Data Index: 6096840 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.9422. Min Act: -0.1700
Data Index: 6368726 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.8797. Min Act: -0.1700
Data Index: 2718784 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.7547. Min Act: -0.1700
Data Index: 2380693 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.7234. Min Act: -0.1700
Data Index: 4843451 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.6609. Min Act: -0.1700
Data Index: 6199803 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.6609. Min Act: -0.1700
Data Index: 8109692 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.5359. Min Act: -0.1700
Data Index: 2948782 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.5359. Min Act: -0.1700
Data Index: 2942465 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.5047. Min Act: -0.1700
Data Index: 8008465 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.5047. Min Act: -0.1700
Data Index: 5454034 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.4422. Min Act: -0.1700
Data Index: 472347 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.4422. Min Act: -0.1700
Data Index: 4020351 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3484. Min Act: -0.1700
Data Index: 3452323 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3797. Min Act: -0.1700
Data Index: 608520 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3484. Min Act: -0.1700
Data Index: 3697702 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3797. Min Act: -0.1700
Data Index: 6309603 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3172. Min Act: -0.1700
Data Index: 5392320 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3172. Min Act: -0.1700
Data Index: 7292408 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0359. Min Range: -8.0359
Max Act: 7.3172. Min Act: -0.1700
Data Index: 8236480 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19