Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5889 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.5522. Min Act: -0.1700
Data Index: 7021903 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.5210. Min Act: -0.1700
Data Index: 6796755 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.4897. Min Act: -0.1700
Data Index: 6190528 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.4272. Min Act: -0.1700
Data Index: 5007106 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.3335. Min Act: -0.1700
Data Index: 6190520 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.3335. Min Act: -0.1700
Data Index: 4747611 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.2710. Min Act: -0.1700
Data Index: 5559111 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.2085. Min Act: -0.1700
Data Index: 3467509 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1772. Min Act: -0.1700
Data Index: 6752410 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1460. Min Act: -0.1700
Data Index: 3127571 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1147. Min Act: -0.1700
Data Index: 8262846 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1460. Min Act: -0.1700
Data Index: 1539798 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1147. Min Act: -0.1700
Data Index: 5616362 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1147. Min Act: -0.1700
Data Index: 3078689 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.1147. Min Act: -0.1700
Data Index: 5811708 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.0835. Min Act: -0.1700
Data Index: 74012 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.0835. Min Act: -0.1700
Data Index: 8497808 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.0835. Min Act: -0.1700
Data Index: 4634555 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.0835. Min Act: -0.1700
Data Index: 7571465 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5522. Min Range: -6.5522
Max Act: 6.0835. Min Act: -0.1700
Data Index: 4539404 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19