Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.8240. Min Act: -0.1700
Data Index: 5980017 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.4178. Min Act: -0.1700
Data Index: 782197 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.3865. Min Act: -0.1700
Data Index: 4831455 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.3553. Min Act: -0.1700
Data Index: 3256483 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.4178. Min Act: -0.1700
Data Index: 6722110 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.2928. Min Act: -0.1700
Data Index: 5509821 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.2615. Min Act: -0.1700
Data Index: 156037 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.2615. Min Act: -0.1700
Data Index: 3159000 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.1678. Min Act: -0.1700
Data Index: 5108331 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.1365. Min Act: -0.1700
Data Index: 3831801 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.1365. Min Act: -0.1700
Data Index: 4513907 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.1365. Min Act: -0.1700
Data Index: 6491949 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.1053. Min Act: -0.1700
Data Index: 1445127 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0740. Min Act: -0.1700
Data Index: 7039340 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0428. Min Act: -0.1700
Data Index: 1701234 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0428. Min Act: -0.1700
Data Index: 5695210 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0428. Min Act: -0.1700
Data Index: 8773453 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0115. Min Act: -0.1700
Data Index: 3235806 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0115. Min Act: -0.1700
Data Index: 4958547 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8240. Min Range: -6.8240
Max Act: 6.0115. Min Act: -0.1700
Data Index: 5592005 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19