Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.5028. Min Act: -0.1700
Data Index: 7903034 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.1590. Min Act: -0.1700
Data Index: 7843023 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.1278. Min Act: -0.1700
Data Index: 2853194 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.0653. Min Act: -0.1700
Data Index: 4255481 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.0340. Min Act: -0.1700
Data Index: 5298646 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.0340. Min Act: -0.1700
Data Index: 4255491 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5028. Min Range: -6.5028
Max Act: 6.0340. Min Act: -0.1700
Data Index: 8045678 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.9403. Min Act: -0.1700
Data Index: 450469 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.9403. Min Act: -0.1700
Data Index: 4097882 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.9090. Min Act: -0.1700
Data Index: 5398505 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.9090. Min Act: -0.1700
Data Index: 324273 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.8778. Min Act: -0.1700
Data Index: 5062041 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.8153. Min Act: -0.1700
Data Index: 477401 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.8153. Min Act: -0.1700
Data Index: 8590805 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.8153. Min Act: -0.1700
Data Index: 5088390 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.8153. Min Act: -0.1700
Data Index: 1305091 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.7840. Min Act: -0.1700
Data Index: 783087 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.7528. Min Act: -0.1700
Data Index: 2835090 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.7215. Min Act: -0.1700
Data Index: 5315007 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5028. Min Range: -6.5028
Max Act: 5.7528. Min Act: -0.1700
Data Index: 4117271 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19