Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4481 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.8783. Min Act: -0.1700
Data Index: 2445610 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.8158. Min Act: -0.1700
Data Index: 8013861 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.7221. Min Act: -0.1700
Data Index: 7119647 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.6283. Min Act: -0.1700
Data Index: 1123605 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.5658. Min Act: -0.1700
Data Index: 3606282 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.5346. Min Act: -0.1700
Data Index: 6826493 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.5033. Min Act: -0.1700
Data Index: 710976 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.4721. Min Act: -0.1700
Data Index: 1007003 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.4721. Min Act: -0.1700
Data Index: 4652884 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.4408. Min Act: -0.1700
Data Index: 4229013 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3783. Min Act: -0.1700
Data Index: 2654581 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.4096. Min Act: -0.1700
Data Index: 6690004 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3783. Min Act: -0.1700
Data Index: 8692916 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3471. Min Act: -0.1700
Data Index: 5443567 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3471. Min Act: -0.1700
Data Index: 7101890 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3471. Min Act: -0.1700
Data Index: 1133542 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3471. Min Act: -0.1700
Data Index: 2781358 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3471. Min Act: -0.1700
Data Index: 3655785 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3158. Min Act: -0.1700
Data Index: 5916729 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8783. Min Range: -6.8783
Max Act: 6.3158. Min Act: -0.1700
Data Index: 5579766 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19