Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.5609. Min Act: -0.1700
Data Index: 6076216 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.2796. Min Act: -0.1700
Data Index: 7089053 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.1859. Min Act: -0.1700
Data Index: 1264523 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.1859. Min Act: -0.1700
Data Index: 252592 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.0609. Min Act: -0.1700
Data Index: 4581897 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.0609. Min Act: -0.1700
Data Index: 8007287 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.0296. Min Act: -0.1700
Data Index: 738772 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.0609. Min Act: -0.1700
Data Index: 2259122 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5609. Min Range: -6.5609
Max Act: 6.0296. Min Act: -0.1700
Data Index: 6413427 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.9359. Min Act: -0.1700
Data Index: 3409775 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.8734. Min Act: -0.1700
Data Index: 3230108 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.9046. Min Act: -0.1700
Data Index: 87413 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.8734. Min Act: -0.1700
Data Index: 6294504 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.8421. Min Act: -0.1700
Data Index: 4294647 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.8421. Min Act: -0.1700
Data Index: 7513280 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.8109. Min Act: -0.1700
Data Index: 7982150 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.8109. Min Act: -0.1700
Data Index: 588480 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.7796. Min Act: -0.1700
Data Index: 3849147 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.7484. Min Act: -0.1700
Data Index: 4991426 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5609. Min Range: -6.5609
Max Act: 5.7484. Min Act: -0.1700
Data Index: 6798556 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19