Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6246 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1598. Min Range: -11.1598
Max Act: 11.1598. Min Act: -0.1700
Data Index: 6287015 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.8473. Min Act: -0.1700
Data Index: 7465534 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.8473. Min Act: -0.1700
Data Index: 7375978 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.7848. Min Act: -0.1700
Data Index: 7987184 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.7848. Min Act: -0.1700
Data Index: 3909742 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.7223. Min Act: -0.1700
Data Index: 4832793 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.5973. Min Act: -0.1700
Data Index: 7199321 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.5973. Min Act: -0.1700
Data Index: 6263368 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.5348. Min Act: -0.1700
Data Index: 7866918 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.5348. Min Act: -0.1700
Data Index: 4973445 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.5348. Min Act: -0.1700
Data Index: 3845638 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4723. Min Act: -0.1700
Data Index: 7071931 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4723. Min Act: -0.1700
Data Index: 2412692 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4723. Min Act: -0.1700
Data Index: 5248559 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4723. Min Act: -0.1700
Data Index: 7679274 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4723. Min Act: -0.1700
Data Index: 3983280 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4098. Min Act: -0.1700
Data Index: 6838368 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.3473. Min Act: -0.1700
Data Index: 5482320 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4098. Min Act: -0.1700
Data Index: 6586830 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1598. Min Range: -11.1598
Max Act: 10.4098. Min Act: -0.1700
Data Index: 5382587 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19