Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 710 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0876. Min Range: -8.0876
Max Act: 8.0876. Min Act: -0.1700
Data Index: 5672800 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0876. Min Range: -8.0876
Max Act: 8.0251. Min Act: -0.1700
Data Index: 7463011 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0876. Min Range: -8.0876
Max Act: 8.0876. Min Act: -0.1700
Data Index: 3404139 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.8689. Min Act: -0.1700
Data Index: 3407070 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.8376. Min Act: -0.1700
Data Index: 7840953 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.8064. Min Act: -0.1700
Data Index: 3436483 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.7439. Min Act: -0.1700
Data Index: 2202697 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.7126. Min Act: -0.1700
Data Index: 3886677 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.7126. Min Act: -0.1700
Data Index: 346660 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.7126. Min Act: -0.1700
Data Index: 8806401 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.7126. Min Act: -0.1700
Data Index: 4528167 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.7439. Min Act: -0.1700
Data Index: 2325814 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.6814. Min Act: -0.1700
Data Index: 6522129 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.6189. Min Act: -0.1700
Data Index: 5035750 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.6189. Min Act: -0.1700
Data Index: 6871674 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.6501. Min Act: -0.1700
Data Index: 2508847 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.6814. Min Act: -0.1700
Data Index: 4618905 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.6189. Min Act: -0.1700
Data Index: 6480920 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.5564. Min Act: -0.1700
Data Index: 1259008 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0876. Min Range: -8.0876
Max Act: 7.4939. Min Act: -0.1700
Data Index: 8157937 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19