Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.4271. Min Act: -0.1700
Data Index: 423226 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2396. Min Act: -0.1700
Data Index: 5108046 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2396. Min Act: -0.1700
Data Index: 6541033 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2396. Min Act: -0.1700
Data Index: 8110304 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2396. Min Act: -0.1700
Data Index: 3139163 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2708. Min Act: -0.1700
Data Index: 7757576 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2083. Min Act: -0.1700
Data Index: 2203221 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2083. Min Act: -0.1700
Data Index: 6528395 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2083. Min Act: -0.1700
Data Index: 3889353 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2083. Min Act: -0.1700
Data Index: 1890395 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2083. Min Act: -0.1700
Data Index: 2370475 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.2083. Min Act: -0.1700
Data Index: 2375885 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 8065232 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 3821999 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 3623305 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 3574495 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1458. Min Act: -0.1700
Data Index: 1452349 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 7485091 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 2445431 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4271. Min Range: -4.4271
Max Act: 4.1770. Min Act: -0.1700
Data Index: 6676534 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19