Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4044. Min Act: -0.1700
Data Index: 6838315 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 7783383 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 1988966 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 5126261 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 4478139 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3419. Min Act: -0.1700
Data Index: 7524759 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3419. Min Act: -0.1700
Data Index: 4335682 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3419. Min Act: -0.1700
Data Index: 1247743 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3419. Min Act: -0.1700
Data Index: 8681879 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3419. Min Act: -0.1700
Data Index: 7425914 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3107. Min Act: -0.1700
Data Index: 8140443 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2794. Min Act: -0.1700
Data Index: 3799450 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3107. Min Act: -0.1700
Data Index: 2007277 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 435386 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 1907572 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2794. Min Act: -0.1700
Data Index: 646682 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 1299825 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 7137932 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 7509431 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 4138574 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19