Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6028 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3235. Min Range: -5.3235
Max Act: 5.3235. Min Act: -0.1700
Data Index: 7566823 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3235. Min Range: -5.3235
Max Act: 5.2298. Min Act: -0.1700
Data Index: 330241 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3235. Min Range: -5.3235
Max Act: 5.1360. Min Act: -0.1700
Data Index: 535427 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3235. Min Range: -5.3235
Max Act: 5.0735. Min Act: -0.1700
Data Index: 4863662 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3235. Min Range: -5.3235
Max Act: 5.0110. Min Act: -0.1700
Data Index: 2518406 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3235. Min Range: -5.3235
Max Act: 5.0110. Min Act: -0.1700
Data Index: 2887629 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9798. Min Act: -0.1700
Data Index: 2161655 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9798. Min Act: -0.1700
Data Index: 8788547 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9485. Min Act: -0.1700
Data Index: 4325727 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9798. Min Act: -0.1700
Data Index: 607652 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9485. Min Act: -0.1700
Data Index: 2996336 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9485. Min Act: -0.1700
Data Index: 3985867 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9485. Min Act: -0.1700
Data Index: 6227657 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9173. Min Act: -0.1700
Data Index: 3915584 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9173. Min Act: -0.1700
Data Index: 1226716 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9173. Min Act: -0.1700
Data Index: 7309429 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9173. Min Act: -0.1700
Data Index: 1230451 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.9173. Min Act: -0.1700
Data Index: 4397267 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.8860. Min Act: -0.1700
Data Index: 44209 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3235. Min Range: -5.3235
Max Act: 4.8860. Min Act: -0.1700
Data Index: 971263 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19