Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4324 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0726. Min Range: -7.0726
Max Act: 7.0726. Min Act: -0.1700
Data Index: 861785 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.9476. Min Act: -0.1700
Data Index: 7054988 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.8539. Min Act: -0.1700
Data Index: 7578324 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.8539. Min Act: -0.1700
Data Index: 7445630 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.6664. Min Act: -0.1700
Data Index: 4908218 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.6351. Min Act: -0.1700
Data Index: 2817888 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.6039. Min Act: -0.1700
Data Index: 1593338 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.5414. Min Act: -0.1700
Data Index: 5434612 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.5101. Min Act: -0.1700
Data Index: 5102821 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.5101. Min Act: -0.1700
Data Index: 4006579 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4789. Min Act: -0.1700
Data Index: 4827866 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4476. Min Act: -0.1700
Data Index: 2938178 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4789. Min Act: -0.1700
Data Index: 644451 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4476. Min Act: -0.1700
Data Index: 6288946 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4476. Min Act: -0.1700
Data Index: 6549873 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4476. Min Act: -0.1700
Data Index: 3796916 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4789. Min Act: -0.1700
Data Index: 7021276 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4476. Min Act: -0.1700
Data Index: 3667962 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.4164. Min Act: -0.1700
Data Index: 6966407 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0726. Min Range: -7.0726
Max Act: 6.3851. Min Act: -0.1700
Data Index: 4597068 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19