Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.8003. Min Act: -0.1700
Data Index: 5026357 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.7378. Min Act: -0.1700
Data Index: 3574531 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.7378. Min Act: -0.1700
Data Index: 8297348 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.6128. Min Act: -0.1700
Data Index: 1712789 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.5815. Min Act: -0.1700
Data Index: 6146284 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.5503. Min Act: -0.1700
Data Index: 5275329 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.5190. Min Act: -0.1700
Data Index: 273522 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.5190. Min Act: -0.1700
Data Index: 6499491 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4878. Min Act: -0.1700
Data Index: 1855638 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4878. Min Act: -0.1700
Data Index: 237328 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4878. Min Act: -0.1700
Data Index: 1211364 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4253. Min Act: -0.1700
Data Index: 1585156 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4565. Min Act: -0.1700
Data Index: 7493542 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4253. Min Act: -0.1700
Data Index: 7180756 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4565. Min Act: -0.1700
Data Index: 6402906 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.3940. Min Act: -0.1700
Data Index: 6309580 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.3940. Min Act: -0.1700
Data Index: 3636168 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.4253. Min Act: -0.1700
Data Index: 3703668 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.3940. Min Act: -0.1700
Data Index: 6286862 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8003. Min Range: -6.8003
Max Act: 6.3628. Min Act: -0.1700
Data Index: 7904175 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19