Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.3666. Min Act: -0.1700
Data Index: 8443692 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.3509. Min Act: -0.1700
Data Index: 460220 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.3195. Min Act: -0.1700
Data Index: 1895291 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.2253. Min Act: -0.1700
Data Index: 972246 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1781. Min Act: -0.1700
Data Index: 5338714 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1781. Min Act: -0.1700
Data Index: 8038497 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1624. Min Act: -0.1700
Data Index: 8509750 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1624. Min Act: -0.1700
Data Index: 2992919 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1466. Min Act: -0.1700
Data Index: 2844229 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1309. Min Act: -0.1700
Data Index: 6787182 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1309. Min Act: -0.1700
Data Index: 3552192 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1151. Min Act: -0.1700
Data Index: 7588858 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1151. Min Act: -0.1700
Data Index: 1118236 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.0836. Min Act: -0.1700
Data Index: 6227238 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.1151. Min Act: -0.1700
Data Index: 6697215 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.0836. Min Act: -0.1700
Data Index: 3511600 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.0836. Min Act: -0.1700
Data Index: 6309799 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.0679. Min Act: -0.1700
Data Index: 504169 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.0679. Min Act: -0.1700
Data Index: 2853253 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3666. Min Range: -3.3666
Max Act: 3.0521. Min Act: -0.1700
Data Index: 2689038 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19