Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0541. Min Range: -4.0541
Max Act: 4.0541. Min Act: -0.1700
Data Index: 3084240 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0541. Min Range: -4.0541
Max Act: 4.0072. Min Act: -0.1700
Data Index: 3039675 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.9290. Min Act: -0.1700
Data Index: 8596052 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8821. Min Act: -0.1700
Data Index: 8400912 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8821. Min Act: -0.1700
Data Index: 8292621 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8821. Min Act: -0.1700
Data Index: 3871951 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8509. Min Act: -0.1700
Data Index: 5017830 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8352. Min Act: -0.1700
Data Index: 2240713 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7883. Min Act: -0.1700
Data Index: 7946596 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7727. Min Act: -0.1700
Data Index: 7944746 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7414. Min Act: -0.1700
Data Index: 4107882 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7414. Min Act: -0.1700
Data Index: 3411969 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7101. Min Act: -0.1700
Data Index: 8455666 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6945. Min Act: -0.1700
Data Index: 8411696 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6788. Min Act: -0.1700
Data Index: 4963734 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6788. Min Act: -0.1700
Data Index: 1168376 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6475. Min Act: -0.1700
Data Index: 8656946 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6788. Min Act: -0.1700
Data Index: 1077459 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6632. Min Act: -0.1700
Data Index: 4543787 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.6632. Min Act: -0.1700
Data Index: 7086377 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19