Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.4883. Min Act: -0.1700
Data Index: 4895674 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.5195. Min Act: -0.1700
Data Index: 7337899 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.4883. Min Act: -0.1700
Data Index: 919772 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.3945. Min Act: -0.1700
Data Index: 7263908 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.3945. Min Act: -0.1700
Data Index: 6633915 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.3945. Min Act: -0.1700
Data Index: 1902396 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.3008. Min Act: -0.1700
Data Index: 6485263 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2695. Min Act: -0.1700
Data Index: 1653422 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2695. Min Act: -0.1700
Data Index: 3627016 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2695. Min Act: -0.1700
Data Index: 7407595 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2695. Min Act: -0.1700
Data Index: 4025307 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2383. Min Act: -0.1700
Data Index: 8746710 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2695. Min Act: -0.1700
Data Index: 3287129 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2383. Min Act: -0.1700
Data Index: 987736 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2070. Min Act: -0.1700
Data Index: 2772879 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.2070. Min Act: -0.1700
Data Index: 3451754 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.1758. Min Act: -0.1700
Data Index: 1213182 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.1758. Min Act: -0.1700
Data Index: 7428682 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.1758. Min Act: -0.1700
Data Index: 3983541 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5195. Min Range: -5.5195
Max Act: 5.1758. Min Act: -0.1700
Data Index: 7553113 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19