Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1655. Min Range: -7.1655
Max Act: 7.1655. Min Act: -0.1700
Data Index: 2571500 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1655. Min Range: -7.1655
Max Act: 7.0405. Min Act: -0.1700
Data Index: 1453041 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1655. Min Range: -7.1655
Max Act: 7.0405. Min Act: -0.1700
Data Index: 424963 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1655. Min Range: -7.1655
Max Act: 7.0092. Min Act: -0.1700
Data Index: 6650321 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9780. Min Act: -0.1700
Data Index: 510268 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9780. Min Act: -0.1700
Data Index: 6222178 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9155. Min Act: -0.1700
Data Index: 3731665 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9155. Min Act: -0.1700
Data Index: 6058242 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9467. Min Act: -0.1700
Data Index: 2834976 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9155. Min Act: -0.1700
Data Index: 6591619 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.9155. Min Act: -0.1700
Data Index: 6064453 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8842. Min Act: -0.1700
Data Index: 5813090 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8842. Min Act: -0.1700
Data Index: 8484347 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8842. Min Act: -0.1700
Data Index: 4239790 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8842. Min Act: -0.1700
Data Index: 8756698 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8217. Min Act: -0.1700
Data Index: 7045034 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8530. Min Act: -0.1700
Data Index: 1108529 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8530. Min Act: -0.1700
Data Index: 5467921 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8530. Min Act: -0.1700
Data Index: 6774531 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1655. Min Range: -7.1655
Max Act: 6.8530. Min Act: -0.1700
Data Index: 6411347 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19