Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0697. Min Range: -4.0697
Max Act: 4.0697. Min Act: -0.1700
Data Index: 6650653 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.8822. Min Act: -0.1700
Data Index: 7755419 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.8196. Min Act: -0.1700
Data Index: 6441960 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6945. Min Act: -0.1700
Data Index: 3742722 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6945. Min Act: -0.1700
Data Index: 802992 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6632. Min Act: -0.1700
Data Index: 25595 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6319. Min Act: -0.1700
Data Index: 6152327 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6632. Min Act: -0.1700
Data Index: 4577223 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6319. Min Act: -0.1700
Data Index: 3146129 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6319. Min Act: -0.1700
Data Index: 3301794 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6006. Min Act: -0.1700
Data Index: 4153575 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6006. Min Act: -0.1700
Data Index: 2519982 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6006. Min Act: -0.1700
Data Index: 1349940 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.5693. Min Act: -0.1700
Data Index: 2651698 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.5693. Min Act: -0.1700
Data Index: 4048324 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.5693. Min Act: -0.1700
Data Index: 5005507 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.5693. Min Act: -0.1700
Data Index: 8605726 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6006. Min Act: -0.1700
Data Index: 8304140 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.5693. Min Act: -0.1700
Data Index: 1755406 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.5380. Min Act: -0.1700
Data Index: 5647630 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19