Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5508 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.7547. Min Act: -0.1700
Data Index: 1716050 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.6297. Min Act: -0.1700
Data Index: 1745600 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5984. Min Act: -0.1700
Data Index: 2288682 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5984. Min Act: -0.1700
Data Index: 4321193 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5984. Min Act: -0.1700
Data Index: 5710145 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5359. Min Act: -0.1700
Data Index: 5284782 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 7386178 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5359. Min Act: -0.1700
Data Index: 864273 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 4975587 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 4876524 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 3463632 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5359. Min Act: -0.1700
Data Index: 8461972 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 5742755 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 1010835 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.5047. Min Act: -0.1700
Data Index: 619261 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.4734. Min Act: -0.1700
Data Index: 1086249 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.4734. Min Act: -0.1700
Data Index: 7802771 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.4109. Min Act: -0.1700
Data Index: 6958646 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.4422. Min Act: -0.1700
Data Index: 169794 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7547. Min Range: -6.7547
Max Act: 6.4734. Min Act: -0.1700
Data Index: 551132 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19