Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.4025. Min Act: -0.1700
Data Index: 2587792 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.4025. Min Act: -0.1700
Data Index: 5537381 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.3554. Min Act: -0.1700
Data Index: 6459221 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.3711. Min Act: -0.1700
Data Index: 5222647 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.3083. Min Act: -0.1700
Data Index: 8162973 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2612. Min Act: -0.1700
Data Index: 4480218 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2612. Min Act: -0.1700
Data Index: 620175 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2612. Min Act: -0.1700
Data Index: 8162968 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2455. Min Act: -0.1700
Data Index: 5810430 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2455. Min Act: -0.1700
Data Index: 6714863 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2298. Min Act: -0.1700
Data Index: 4480214 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.2141. Min Act: -0.1700
Data Index: 4514032 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1984. Min Act: -0.1700
Data Index: 8162975 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1984. Min Act: -0.1700
Data Index: 8820012 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1826. Min Act: -0.1700
Data Index: 2514751 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1984. Min Act: -0.1700
Data Index: 5615324 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1826. Min Act: -0.1700
Data Index: 2387715 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1669. Min Act: -0.1700
Data Index: 2003154 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1669. Min Act: -0.1700
Data Index: 2587791 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4025. Min Range: -3.4025
Max Act: 3.1512. Min Act: -0.1700
Data Index: 6578878 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19