Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.4375. Min Act: -0.1700
Data Index: 4573110 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2812. Min Act: -0.1700
Data Index: 2686110 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2500. Min Act: -0.1700
Data Index: 2081429 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1875. Min Act: -0.1700
Data Index: 23650 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2187. Min Act: -0.1700
Data Index: 422647 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1875. Min Act: -0.1700
Data Index: 7437666 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0937. Min Act: -0.1700
Data Index: 6587102 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0625. Min Act: -0.1700
Data Index: 7542611 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0312. Min Act: -0.1700
Data Index: 4175002 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0312. Min Act: -0.1700
Data Index: 3121009 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0000. Min Act: -0.1700
Data Index: 5580330 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6766294 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6328430 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0000. Min Act: -0.1700
Data Index: 311513 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4375. Min Range: -6.4375
Max Act: 5.9687. Min Act: -0.1700
Data Index: 6911271 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4375. Min Range: -6.4375
Max Act: 5.9687. Min Act: -0.1700
Data Index: 2651343 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4375. Min Range: -6.4375
Max Act: 5.9687. Min Act: -0.1700
Data Index: 3882196 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4375. Min Range: -6.4375
Max Act: 5.9375. Min Act: -0.1700
Data Index: 529533 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4375. Min Range: -6.4375
Max Act: 5.9062. Min Act: -0.1700
Data Index: 4157153 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4375. Min Range: -6.4375
Max Act: 5.9062. Min Act: -0.1700
Data Index: 1692507 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19