Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5211 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.1122. Min Act: -0.1700
Data Index: 2582140 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.0809. Min Act: -0.1700
Data Index: 7310870 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.0497. Min Act: -0.1700
Data Index: 4287135 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.0497. Min Act: -0.1700
Data Index: 5249317 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.0497. Min Act: -0.1700
Data Index: 459229 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.0184. Min Act: -0.1700
Data Index: 4993983 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9872. Min Act: -0.1700
Data Index: 5281743 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9872. Min Act: -0.1699
Data Index: 14115 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1122. Min Range: -6.1122
Max Act: 6.0184. Min Act: -0.1700
Data Index: 6382439 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9872. Min Act: -0.1700
Data Index: 2439915 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9559. Min Act: -0.1700
Data Index: 383623 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9559. Min Act: -0.1700
Data Index: 2127159 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9559. Min Act: -0.1700
Data Index: 6451983 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4998524 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9559. Min Act: -0.1700
Data Index: 5203465 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9559. Min Act: -0.1700
Data Index: 7714656 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.8934. Min Act: -0.1700
Data Index: 3714096 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.8934. Min Act: -0.1700
Data Index: 2356205 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9247. Min Act: -0.1700
Data Index: 3949822 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1122. Min Range: -6.1122
Max Act: 5.9247. Min Act: -0.1700
Data Index: 3951298 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19