Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1947 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.4267. Min Act: -0.1700
Data Index: 6158931 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.4267. Min Act: -0.1700
Data Index: 1664917 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.3642. Min Act: -0.1700
Data Index: 837495 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.3642. Min Act: -0.1700
Data Index: 6135627 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.2705. Min Act: -0.1700
Data Index: 2581994 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.2392. Min Act: -0.1700
Data Index: 7430223 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.2392. Min Act: -0.1700
Data Index: 7304887 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1767. Min Act: -0.1700
Data Index: 307772 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 3839522 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 6656064 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 3779768 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 8220023 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 8138183 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1142. Min Act: -0.1700
Data Index: 4642307 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.0830. Min Act: -0.1700
Data Index: 2941359 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1142. Min Act: -0.1700
Data Index: 1205913 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 5439597 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.1455. Min Act: -0.1700
Data Index: 7607437 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.0830. Min Act: -0.1700
Data Index: 6230347 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4267. Min Range: -6.4267
Max Act: 6.0517. Min Act: -0.1700
Data Index: 4782741 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19