Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1628. Min Range: -5.1628
Max Act: 5.1628. Min Act: -0.1700
Data Index: 388933 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1628. Min Range: -5.1628
Max Act: 5.0378. Min Act: -0.1700
Data Index: 5023450 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.8503. Min Act: -0.1700
Data Index: 8097312 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7566. Min Act: -0.1700
Data Index: 4502336 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6941. Min Act: -0.1700
Data Index: 3520393 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6941. Min Act: -0.1700
Data Index: 1213877 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6628. Min Act: -0.1700
Data Index: 1649225 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6628. Min Act: -0.1700
Data Index: 4023915 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6316. Min Act: -0.1700
Data Index: 4928044 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5691. Min Act: -0.1700
Data Index: 6156329 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5691. Min Act: -0.1700
Data Index: 4713945 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5691. Min Act: -0.1700
Data Index: 1994142 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5691. Min Act: -0.1700
Data Index: 1658331 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5378. Min Act: -0.1700
Data Index: 3069397 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5378. Min Act: -0.1700
Data Index: 3393846 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5378. Min Act: -0.1700
Data Index: 3190568 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5378. Min Act: -0.1700
Data Index: 1898953 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5378. Min Act: -0.1699
Data Index: 5515527 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5066. Min Act: -0.1700
Data Index: 2339460 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.5066. Min Act: -0.1700
Data Index: 596515 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19