Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5258 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.4182. Min Act: -0.1700
Data Index: 1184349 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.4182. Min Act: -0.1700
Data Index: 486910 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.1682. Min Act: -0.1700
Data Index: 2135889 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.1057. Min Act: -0.1700
Data Index: 6484207 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.1057. Min Act: -0.1700
Data Index: 2146438 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.0432. Min Act: -0.1700
Data Index: 4788648 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4182. Min Range: -8.4182
Max Act: 8.0432. Min Act: -0.1700
Data Index: 4610043 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.9807. Min Act: -0.1700
Data Index: 5245158 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.9182. Min Act: -0.1700
Data Index: 2523390 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.8557. Min Act: -0.1700
Data Index: 7382483 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.8557. Min Act: -0.1700
Data Index: 6802548 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.8557. Min Act: -0.1700
Data Index: 1334396 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.8557. Min Act: -0.1700
Data Index: 6972879 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.8557. Min Act: -0.1700
Data Index: 5598832 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.7307. Min Act: -0.1700
Data Index: 257424 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.7307. Min Act: -0.1700
Data Index: 1745341 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.7307. Min Act: -0.1700
Data Index: 3969780 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.7307. Min Act: -0.1700
Data Index: 1659038 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.7307. Min Act: -0.1700
Data Index: 1204116 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4182. Min Range: -8.4182
Max Act: 7.6682. Min Act: -0.1700
Data Index: 4232354 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19