Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5982 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.4250. Min Act: -0.1700
Data Index: 2151085 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3312. Min Act: -0.1700
Data Index: 7387154 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3000. Min Act: -0.1700
Data Index: 2249582 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3312. Min Act: -0.1700
Data Index: 6549068 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3312. Min Act: -0.1700
Data Index: 4284995 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3000. Min Act: -0.1700
Data Index: 6419118 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3000. Min Act: -0.1700
Data Index: 5607779 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2687. Min Act: -0.1700
Data Index: 6864638 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2687. Min Act: -0.1700
Data Index: 4351379 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2375. Min Act: -0.1700
Data Index: 5081257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 8019793 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 3627769 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 2644418 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 5502521 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 8072627 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.1750. Min Act: -0.1700
Data Index: 2052041 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.1750. Min Act: -0.1700
Data Index: 4338081 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.1437. Min Act: -0.1700
Data Index: 628663 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 8499496 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.1750. Min Act: -0.1700
Data Index: 1027965 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19