Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0114. Min Range: -5.0114
Max Act: 5.0114. Min Act: -0.1700
Data Index: 5368652 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.8864. Min Act: -0.1700
Data Index: 4151254 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.8551. Min Act: -0.1700
Data Index: 695648 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.8239. Min Act: -0.1700
Data Index: 7316158 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.7926. Min Act: -0.1700
Data Index: 4860871 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6989. Min Act: -0.1700
Data Index: 6963747 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6364. Min Act: -0.1700
Data Index: 2558521 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6364. Min Act: -0.1700
Data Index: 7578007 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6364. Min Act: -0.1700
Data Index: 3181702 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 7921192 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 6719872 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 2099978 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 7328702 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 3642063 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.5739. Min Act: -0.1700
Data Index: 4618751 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.5739. Min Act: -0.1700
Data Index: 5598931 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.5739. Min Act: -0.1700
Data Index: 2151006 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.5426. Min Act: -0.1700
Data Index: 4580283 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.5739. Min Act: -0.1700
Data Index: 117062 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.5114. Min Act: -0.1700
Data Index: 2726960 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19