Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0191. Min Range: -5.0191
Max Act: 5.0191. Min Act: -0.1700
Data Index: 2895463 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.9566. Min Act: -0.1700
Data Index: 907211 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.9253. Min Act: -0.1700
Data Index: 5303062 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.9253. Min Act: -0.1700
Data Index: 4284108 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.9253. Min Act: -0.1700
Data Index: 3160570 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8941. Min Act: -0.1700
Data Index: 3105194 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8628. Min Act: -0.1700
Data Index: 5915420 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4369231 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8003. Min Act: -0.1700
Data Index: 6658692 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8003. Min Act: -0.1700
Data Index: 2631666 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8003. Min Act: -0.1700
Data Index: 7931646 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7691. Min Act: -0.1700
Data Index: 3380566 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.8003. Min Act: -0.1700
Data Index: 8441335 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7691. Min Act: -0.1700
Data Index: 6222457 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7691. Min Act: -0.1700
Data Index: 1495558 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7691. Min Act: -0.1700
Data Index: 5335025 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7066. Min Act: -0.1700
Data Index: 7236626 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7378. Min Act: -0.1700
Data Index: 3657318 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7378. Min Act: -0.1700
Data Index: 1958335 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0191. Min Range: -5.0191
Max Act: 4.7378. Min Act: -0.1700
Data Index: 444917 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19