Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.4008. Min Act: -0.1700
Data Index: 7786627 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.3383. Min Act: -0.1700
Data Index: 3363570 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.3071. Min Act: -0.1700
Data Index: 7052024 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.3383. Min Act: -0.1700
Data Index: 7586975 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.3383. Min Act: -0.1700
Data Index: 4416895 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.3071. Min Act: -0.1700
Data Index: 3536396 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.3071. Min Act: -0.1700
Data Index: 561735 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2758. Min Act: -0.1700
Data Index: 7499330 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2758. Min Act: -0.1700
Data Index: 734715 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2758. Min Act: -0.1700
Data Index: 470151 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2758. Min Act: -0.1700
Data Index: 2147377 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2758. Min Act: -0.1700
Data Index: 7717203 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2758. Min Act: -0.1700
Data Index: 6052657 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2446. Min Act: -0.1700
Data Index: 7689064 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2446. Min Act: -0.1700
Data Index: 6407107 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2133. Min Act: -0.1700
Data Index: 7770010 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2446. Min Act: -0.1700
Data Index: 6077078 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2446. Min Act: -0.1700
Data Index: 3198037 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2446. Min Act: -0.1700
Data Index: 2625195 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4008. Min Range: -5.4008
Max Act: 5.2133. Min Act: -0.1700
Data Index: 703832 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19