Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5417 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.1856. Min Act: -0.1700
Data Index: 5999565 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.0606. Min Act: -0.1700
Data Index: 3684773 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.0606. Min Act: -0.1700
Data Index: 5131002 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.0293. Min Act: -0.1700
Data Index: 6645020 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9981. Min Act: -0.1700
Data Index: 5489524 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9981. Min Act: -0.1700
Data Index: 41645 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9981. Min Act: -0.1700
Data Index: 6556518 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.0293. Min Act: -0.1700
Data Index: 1829770 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9981. Min Act: -0.1700
Data Index: 5482094 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.0293. Min Act: -0.1700
Data Index: 5417232 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1856. Min Range: -4.1856
Max Act: 4.0293. Min Act: -0.1700
Data Index: 1529181 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9981. Min Act: -0.1700
Data Index: 4827730 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9981. Min Act: -0.1700
Data Index: 1262265 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9668. Min Act: -0.1700
Data Index: 5035250 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9668. Min Act: -0.1700
Data Index: 7458434 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9668. Min Act: -0.1700
Data Index: 1597906 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9355. Min Act: -0.1700
Data Index: 1206313 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9668. Min Act: -0.1700
Data Index: 6793843 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9355. Min Act: -0.1700
Data Index: 2071318 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1856. Min Range: -4.1856
Max Act: 3.9668. Min Act: -0.1700
Data Index: 5087926 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19