Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5270 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.6109. Min Act: -0.1700
Data Index: 7789814 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.5172. Min Act: -0.1700
Data Index: 8657427 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.3922. Min Act: -0.1700
Data Index: 8055863 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.3297. Min Act: -0.1700
Data Index: 3435079 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.3297. Min Act: -0.1700
Data Index: 4225357 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.2672. Min Act: -0.1700
Data Index: 7566552 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.2047. Min Act: -0.1700
Data Index: 2999839 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0484. Min Act: -0.1700
Data Index: 5961871 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0797. Min Act: -0.1700
Data Index: 8733964 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0484. Min Act: -0.1700
Data Index: 8490852 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0484. Min Act: -0.1700
Data Index: 5648500 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0484. Min Act: -0.1700
Data Index: 648735 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0484. Min Act: -0.1700
Data Index: 73934 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0172. Min Act: -0.1700
Data Index: 5582491 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0172. Min Act: -0.1700
Data Index: 8751867 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6109. Min Range: -6.6109
Max Act: 5.9859. Min Act: -0.1700
Data Index: 3177994 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6109. Min Range: -6.6109
Max Act: 5.9859. Min Act: -0.1700
Data Index: 7496241 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6109. Min Range: -6.6109
Max Act: 6.0172. Min Act: -0.1700
Data Index: 8199949 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6109. Min Range: -6.6109
Max Act: 5.9547. Min Act: -0.1700
Data Index: 5279934 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6109. Min Range: -6.6109
Max Act: 5.9234. Min Act: -0.1700
Data Index: 6286127 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19