Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 512 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.2308. Min Act: -0.1700
Data Index: 74410 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.1683. Min Act: -0.1700
Data Index: 575609 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 1613623 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0745. Min Act: -0.1700
Data Index: 1509545 (Python Code)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.1058. Min Act: -0.1700
Data Index: 1139344 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.1058. Min Act: -0.1700
Data Index: 742456 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0745. Min Act: -0.1700
Data Index: 583817 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.1058. Min Act: -0.1700
Data Index: 206744 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0745. Min Act: -0.1700
Data Index: 1361929 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0745. Min Act: -0.1700
Data Index: 708580 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0120. Min Act: -0.1700
Data Index: 1649089 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0120. Min Act: -0.1700
Data Index: 1402679 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0745. Min Act: -0.1700
Data Index: 1570986 (Python Code)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 1374089 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 1351881 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 171000 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 876272 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 1221170 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 506405 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2308. Min Range: -6.2308
Max Act: 6.0433. Min Act: -0.1700
Data Index: 861437 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19