Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0003. Min Range: -6.0003
Max Act: 6.0003. Min Act: -0.1700
Data Index: 7461785 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.9066. Min Act: -0.1700
Data Index: 171056 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2815086 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.9066. Min Act: -0.1700
Data Index: 8279041 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.8753. Min Act: -0.1700
Data Index: 6130893 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.7816. Min Act: -0.1700
Data Index: 3456324 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.7816. Min Act: -0.1700
Data Index: 2277037 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.7816. Min Act: -0.1700
Data Index: 3872777 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.7191. Min Act: -0.1700
Data Index: 8180395 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6878. Min Act: -0.1700
Data Index: 2820432 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.7191. Min Act: -0.1700
Data Index: 5879777 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.7191. Min Act: -0.1700
Data Index: 4413562 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6878. Min Act: -0.1700
Data Index: 5968072 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6566. Min Act: -0.1700
Data Index: 5392407 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6878. Min Act: -0.1700
Data Index: 7466897 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6878. Min Act: -0.1700
Data Index: 6942416 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6566. Min Act: -0.1700
Data Index: 2400305 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.5941. Min Act: -0.1700
Data Index: 7422226 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.6253. Min Act: -0.1700
Data Index: 2400304 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0003. Min Range: -6.0003
Max Act: 5.5628. Min Act: -0.1700
Data Index: 5071352 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19