Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.7770. Min Act: -0.1700
Data Index: 8124346 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.5582. Min Act: -0.1700
Data Index: 1888714 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.4645. Min Act: -0.1700
Data Index: 295942 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.4957. Min Act: -0.1700
Data Index: 3147194 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.4645. Min Act: -0.1700
Data Index: 3567085 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.4020. Min Act: -0.1700
Data Index: 8175603 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.4020. Min Act: -0.1700
Data Index: 402736 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.4020. Min Act: -0.1700
Data Index: 3989807 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.3707. Min Act: -0.1700
Data Index: 8153851 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.3707. Min Act: -0.1700
Data Index: 5687913 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.3082. Min Act: -0.1700
Data Index: 5678845 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.3082. Min Act: -0.1700
Data Index: 2442982 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.3082. Min Act: -0.1700
Data Index: 4667682 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.3394. Min Act: -0.1700
Data Index: 4832966 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.2769. Min Act: -0.1700
Data Index: 203401 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.2769. Min Act: -0.1700
Data Index: 8585116 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.2769. Min Act: -0.1700
Data Index: 3419997 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.2457. Min Act: -0.1700
Data Index: 250677 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.2457. Min Act: -0.1700
Data Index: 4283535 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7770. Min Range: -4.7770
Max Act: 4.2457. Min Act: -0.1700
Data Index: 4662254 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19