Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2112 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1149. Min Range: -8.1149
Max Act: 8.1149. Min Act: -0.1700
Data Index: 6924637 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.9274. Min Act: -0.1700
Data Index: 7517470 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.8649. Min Act: -0.1700
Data Index: 8672624 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.8649. Min Act: -0.1700
Data Index: 4062845 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.8649. Min Act: -0.1700
Data Index: 1474872 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7711. Min Act: -0.1700
Data Index: 2769426 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7711. Min Act: -0.1700
Data Index: 4443923 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7086. Min Act: -0.1700
Data Index: 8062554 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6149. Min Act: -0.1700
Data Index: 969550 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.5836. Min Act: -0.1700
Data Index: 5953937 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.5836. Min Act: -0.1700
Data Index: 1906133 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6149. Min Act: -0.1700
Data Index: 5043187 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.5836. Min Act: -0.1700
Data Index: 33676 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.5211. Min Act: -0.1700
Data Index: 3064572 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.5211. Min Act: -0.1700
Data Index: 112812 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4586. Min Act: -0.1700
Data Index: 8787192 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4586. Min Act: -0.1700
Data Index: 6509228 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4586. Min Act: -0.1700
Data Index: 601294 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4586. Min Act: -0.1700
Data Index: 3248129 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.3961. Min Act: -0.1700
Data Index: 7875139 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19