Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0861. Min Range: -7.0861
Max Act: 7.0861. Min Act: -0.1700
Data Index: 6399573 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.9924. Min Act: -0.1700
Data Index: 231872 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.9611. Min Act: -0.1700
Data Index: 2151480 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.9299. Min Act: -0.1700
Data Index: 7207143 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8674. Min Act: -0.1700
Data Index: 1374089 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8674. Min Act: -0.1700
Data Index: 799805 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8361. Min Act: -0.1700
Data Index: 1791651 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8361. Min Act: -0.1700
Data Index: 6353143 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8049. Min Act: -0.1700
Data Index: 7097506 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8049. Min Act: -0.1700
Data Index: 3646996 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.8049. Min Act: -0.1700
Data Index: 3988228 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7736. Min Act: -0.1700
Data Index: 8118333 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7736. Min Act: -0.1700
Data Index: 3433323 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7736. Min Act: -0.1700
Data Index: 633176 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7424. Min Act: -0.1700
Data Index: 2035296 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7424. Min Act: -0.1700
Data Index: 2348625 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7111. Min Act: -0.1700
Data Index: 7467426 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7424. Min Act: -0.1700
Data Index: 5948363 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7424. Min Act: -0.1700
Data Index: 2548370 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0861. Min Range: -7.0861
Max Act: 6.7424. Min Act: -0.1700
Data Index: 4738887 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19