Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.9566. Min Act: -0.1700
Data Index: 567809 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.8941. Min Act: -0.1700
Data Index: 6605104 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.8941. Min Act: -0.1700
Data Index: 3469350 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.7691. Min Act: -0.1700
Data Index: 4622513 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.7066. Min Act: -0.1700
Data Index: 3095464 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 2783978 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 1171712 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 3001849 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 1864689 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6441. Min Act: -0.1700
Data Index: 3364903 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6753. Min Act: -0.1700
Data Index: 6607749 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6128. Min Act: -0.1700
Data Index: 2298695 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6128. Min Act: -0.1700
Data Index: 216470 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.5816. Min Act: -0.1700
Data Index: 2187517 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.5816. Min Act: -0.1700
Data Index: 7654636 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.5503. Min Act: -0.1700
Data Index: 366778 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.5191. Min Act: -0.1700
Data Index: 4434332 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4878. Min Act: -0.1700
Data Index: 2102612 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4878. Min Act: -0.1700
Data Index: 4819576 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4878. Min Act: -0.1700
Data Index: 4738647 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19