Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5272 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.4628. Min Act: -0.1700
Data Index: 7735412 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.4628. Min Act: -0.1700
Data Index: 4881641 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.4315. Min Act: -0.1700
Data Index: 6357834 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.4003. Min Act: -0.1700
Data Index: 2820045 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.4003. Min Act: -0.1700
Data Index: 3692188 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6478639 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3378. Min Act: -0.1700
Data Index: 1279893 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3378. Min Act: -0.1700
Data Index: 7926912 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3690. Min Act: -0.1700
Data Index: 945187 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3065. Min Act: -0.1700
Data Index: 4923125 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3065. Min Act: -0.1700
Data Index: 7086092 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5108065 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3065. Min Act: -0.1700
Data Index: 187928 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3065. Min Act: -0.1700
Data Index: 2090797 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.3378. Min Act: -0.1700
Data Index: 4592083 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.2440. Min Act: -0.1700
Data Index: 992192 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.2440. Min Act: -0.1700
Data Index: 5781850 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.2753. Min Act: -0.1700
Data Index: 4757008 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.2440. Min Act: -0.1700
Data Index: 3617206 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4628. Min Range: -5.4628
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5778271 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19