Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.4400. Min Act: -0.1700
Data Index: 5314127 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.3775. Min Act: -0.1700
Data Index: 2765284 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.3775. Min Act: -0.1700
Data Index: 7105658 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.3462. Min Act: -0.1700
Data Index: 2867725 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.3150. Min Act: -0.1700
Data Index: 5561170 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.2837. Min Act: -0.1700
Data Index: 523424 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.2837. Min Act: -0.1700
Data Index: 523431 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.2525. Min Act: -0.1700
Data Index: 2867735 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.2525. Min Act: -0.1700
Data Index: 7105651 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.2212. Min Act: -0.1700
Data Index: 2867723 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.2212. Min Act: -0.1700
Data Index: 2867726 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1900. Min Act: -0.1700
Data Index: 4943171 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1900. Min Act: -0.1700
Data Index: 8161110 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1900. Min Act: -0.1700
Data Index: 7105662 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1900. Min Act: -0.1700
Data Index: 8031779 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1587. Min Act: -0.1700
Data Index: 7361105 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1587. Min Act: -0.1700
Data Index: 3853398 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5314145 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1275. Min Act: -0.1700
Data Index: 8467333 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4400. Min Range: -5.4400
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5719775 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19