Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.5425. Min Act: -0.1700
Data Index: 4729522 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.5425. Min Act: -0.1700
Data Index: 8656190 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.5737. Min Act: -0.1700
Data Index: 4391370 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.5112. Min Act: -0.1700
Data Index: 7144386 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4800. Min Act: -0.1700
Data Index: 1842588 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4800. Min Act: -0.1700
Data Index: 8301290 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4487. Min Act: -0.1700
Data Index: 586826 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4487. Min Act: -0.1700
Data Index: 4397242 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4175. Min Act: -0.1700
Data Index: 4034711 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4487. Min Act: -0.1700
Data Index: 7208935 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4175. Min Act: -0.1700
Data Index: 6345327 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.4175. Min Act: -0.1700
Data Index: 6469278 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3862. Min Act: -0.1700
Data Index: 3925714 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3862. Min Act: -0.1700
Data Index: 4427900 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3862. Min Act: -0.1700
Data Index: 7598296 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2181018 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3550. Min Act: -0.1700
Data Index: 4682120 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3862. Min Act: -0.1700
Data Index: 197209 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3237. Min Act: -0.1700
Data Index: 2780508 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5737. Min Range: -4.5737
Max Act: 4.3237. Min Act: -0.1700
Data Index: 8164782 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19