Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.3800. Min Act: -0.1700
Data Index: 4193537 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.3488. Min Act: -0.1700
Data Index: 965140 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.2863. Min Act: -0.1700
Data Index: 7211185 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.2863. Min Act: -0.1700
Data Index: 1208688 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.1925. Min Act: -0.1700
Data Index: 3936602 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.0675. Min Act: -0.1700
Data Index: 6520518 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.0675. Min Act: -0.1700
Data Index: 800873 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.0675. Min Act: -0.1700
Data Index: 558917 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.0675. Min Act: -0.1700
Data Index: 7211199 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.0050. Min Act: -0.1700
Data Index: 2498650 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3800. Min Range: -6.3800
Max Act: 6.0050. Min Act: -0.1700
Data Index: 1782856 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.9738. Min Act: -0.1700
Data Index: 1208689 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.9425. Min Act: -0.1700
Data Index: 1136705 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.9425. Min Act: -0.1700
Data Index: 8800584 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.9113. Min Act: -0.1700
Data Index: 7921689 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.9113. Min Act: -0.1700
Data Index: 8035657 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.9113. Min Act: -0.1700
Data Index: 675673 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.8488. Min Act: -0.1700
Data Index: 7593605 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.8800. Min Act: -0.1700
Data Index: 5172736 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3800. Min Range: -6.3800
Max Act: 5.8800. Min Act: -0.1700
Data Index: 723094 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19