Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1879 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.7859. Min Act: -0.1700
Data Index: 6675871 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.7234. Min Act: -0.1700
Data Index: 8110620 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.6296. Min Act: -0.1700
Data Index: 1417400 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.5984. Min Act: -0.1700
Data Index: 8245035 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.5984. Min Act: -0.1700
Data Index: 7003198 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.6296. Min Act: -0.1700
Data Index: 5824406 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.5359. Min Act: -0.1700
Data Index: 2677907 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.5046. Min Act: -0.1700
Data Index: 15389 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.5359. Min Act: -0.1700
Data Index: 3627882 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4734. Min Act: -0.1700
Data Index: 5199982 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4109. Min Act: -0.1700
Data Index: 2404729 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4734. Min Act: -0.1700
Data Index: 3317879 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4734. Min Act: -0.1700
Data Index: 120544 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4421. Min Act: -0.1700
Data Index: 2140902 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4109. Min Act: -0.1700
Data Index: 4945061 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.3796. Min Act: -0.1700
Data Index: 7264164 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4109. Min Act: -0.1700
Data Index: 5393073 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.4109. Min Act: -0.1700
Data Index: 8609989 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.3796. Min Act: -0.1700
Data Index: 5474876 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7859. Min Range: -6.7859
Max Act: 6.3796. Min Act: -0.1700
Data Index: 2867154 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19