Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.6809. Min Act: -0.1700
Data Index: 477796 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.5247. Min Act: -0.1700
Data Index: 8626590 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.3997. Min Act: -0.1700
Data Index: 3510475 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.3997. Min Act: -0.1700
Data Index: 851404 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.3372. Min Act: -0.1700
Data Index: 2693340 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.3372. Min Act: -0.1700
Data Index: 7373624 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.2747. Min Act: -0.1700
Data Index: 3622313 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.2747. Min Act: -0.1700
Data Index: 6409573 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.2747. Min Act: -0.1700
Data Index: 6800855 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1809. Min Act: -0.1700
Data Index: 6479113 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.2122. Min Act: -0.1700
Data Index: 4913377 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1809. Min Act: -0.1700
Data Index: 8202030 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1184. Min Act: -0.1700
Data Index: 5369705 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1184. Min Act: -0.1700
Data Index: 1106241 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1184. Min Act: -0.1700
Data Index: 1069970 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1184. Min Act: -0.1700
Data Index: 2514472 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1497. Min Act: -0.1700
Data Index: 2584935 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1184. Min Act: -0.1700
Data Index: 5022575 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1809. Min Act: -0.1700
Data Index: 1722335 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6809. Min Range: -6.6809
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5724943 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19