Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1072 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.4378. Min Act: -0.1700
Data Index: 80097 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.3753. Min Act: -0.1700
Data Index: 5218159 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.3753. Min Act: -0.1700
Data Index: 4568007 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.3128. Min Act: -0.1700
Data Index: 7609574 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.2503. Min Act: -0.1700
Data Index: 919413 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.2191. Min Act: -0.1700
Data Index: 6511717 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.2191. Min Act: -0.1700
Data Index: 5312956 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.2191. Min Act: -0.1700
Data Index: 6858430 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.2191. Min Act: -0.1700
Data Index: 6298902 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.1878. Min Act: -0.1700
Data Index: 4002000 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.1878. Min Act: -0.1700
Data Index: 1901521 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.1253. Min Act: -0.1700
Data Index: 8502235 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.1566. Min Act: -0.1700
Data Index: 8093648 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.1566. Min Act: -0.1700
Data Index: 8086980 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.1253. Min Act: -0.1700
Data Index: 6106549 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.0941. Min Act: -0.1700
Data Index: 4228759 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.0941. Min Act: -0.1700
Data Index: 359118 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.0941. Min Act: -0.1700
Data Index: 3737519 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.0941. Min Act: -0.1700
Data Index: 5657263 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4378. Min Range: -6.4378
Max Act: 6.0941. Min Act: -0.1700
Data Index: 4436712 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19