Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4950 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.4446. Min Act: -0.1700
Data Index: 1982847 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.4133. Min Act: -0.1700
Data Index: 7428618 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3821. Min Act: -0.1700
Data Index: 882856 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3821. Min Act: -0.1700
Data Index: 3473844 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3821. Min Act: -0.1700
Data Index: 231812 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3508. Min Act: -0.1700
Data Index: 231813 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3508. Min Act: -0.1700
Data Index: 6132013 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3196. Min Act: -0.1700
Data Index: 4948240 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3196. Min Act: -0.1700
Data Index: 8557137 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3196. Min Act: -0.1700
Data Index: 3704399 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3196. Min Act: -0.1700
Data Index: 3790604 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 8666897 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 7588608 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 7665615 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 67375 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 3487170 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 1139555 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2883. Min Act: -0.1700
Data Index: 7105493 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.3196. Min Act: -0.1700
Data Index: 6059482 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4446. Min Range: -5.4446
Max Act: 5.2571. Min Act: -0.1700
Data Index: 3844149 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19