Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 529 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.6387. Min Act: -0.1700
Data Index: 7402179 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.4825. Min Act: -0.1700
Data Index: 3721628 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.3887. Min Act: -0.1700
Data Index: 4096646 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.3575. Min Act: -0.1700
Data Index: 8122849 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.2950. Min Act: -0.1700
Data Index: 7402180 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.2325. Min Act: -0.1700
Data Index: 8282774 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.2325. Min Act: -0.1700
Data Index: 5630815 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.2012. Min Act: -0.1700
Data Index: 712153 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.2012. Min Act: -0.1700
Data Index: 2972692 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1700. Min Act: -0.1700
Data Index: 2559278 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1700. Min Act: -0.1700
Data Index: 106001 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1387. Min Act: -0.1700
Data Index: 1819415 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1075. Min Act: -0.1700
Data Index: 5959611 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1075. Min Act: -0.1700
Data Index: 3509010 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1075. Min Act: -0.1700
Data Index: 6500075 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1075. Min Act: -0.1700
Data Index: 3133641 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.0762. Min Act: -0.1700
Data Index: 4096645 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.1075. Min Act: -0.1700
Data Index: 8527109 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.0450. Min Act: -0.1700
Data Index: 2499422 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6387. Min Range: -5.6387
Max Act: 5.0450. Min Act: -0.1700
Data Index: 1761802 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19