Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5623 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1483497 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1426998 (Python Code)

Max Activating Token Index: 406

Text #2

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1496268 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5989. Min Act: -0.0000

Data Index: 597041 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5471. Min Act: -0.0000

Data Index: 810871 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1367739 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1397524 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1645927 (Python Code)

Max Activating Token Index: 456

Text #8

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4270. Min Act: -0.0000

Data Index: 640941 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1312011 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4880. Min Act: -0.0000

Data Index: 395394 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4631. Min Act: -0.0000

Data Index: 616589 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1445712 (Python Code)

Max Activating Token Index: 825

Text #13

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4195. Min Act: -0.0000

Data Index: 312271 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4700. Min Act: -0.0000

Data Index: 987127 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4107. Min Act: -0.0000

Data Index: 827969 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1463901 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4854. Min Act: -0.0000

Data Index: 856076 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4288. Min Act: -0.0000

Data Index: 555790 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1213327 (C4 (Web Text))

Max Activating Token Index: 592