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

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

Neuron 1822 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6363. Min Range: -4.6363

Max Act: 4.6363. Min Act: -0.0000

Data Index: 268225 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 4.6363. Min Range: -4.6363

Max Act: 4.3787. Min Act: -0.0000

Data Index: 1066870 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 4.6363. Min Range: -4.6363

Max Act: 4.2884. Min Act: -0.0000

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.8646. Min Act: -0.0000

Data Index: 870516 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.1712. Min Act: -0.0000

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.9605. Min Act: -0.0001

Data Index: 815555 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 4.6363. Min Range: -4.6363

Max Act: 4.0756. Min Act: -0.0000

Data Index: 66297 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.5043. Min Act: -0.0000

Data Index: 352599 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.7627. Min Act: -0.0000

Data Index: 73384 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.0746. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 4.6363. Min Range: -4.6363

Max Act: 2.9204. Min Act: -0.0001

Data Index: 1079194 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 4.6363. Min Range: -4.6363

Max Act: 2.9839. Min Act: -0.0000

Data Index: 9413 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.1260. Min Act: -0.0000

Data Index: 372888 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 4.6363. Min Range: -4.6363

Max Act: 2.7246. Min Act: -0.0000

Data Index: 456054 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.1920. Min Act: -0.0000

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 4.6363. Min Range: -4.6363

Max Act: 2.7522. Min Act: -0.0001

Data Index: 878655 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 4.6363. Min Range: -4.6363

Max Act: 2.7195. Min Act: -0.0000

Data Index: 333831 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.4124. Min Act: -0.0000

Data Index: 67790 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 4.6363. Min Range: -4.6363

Max Act: 3.0752. Min Act: -0.0001

Data Index: 1265628 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 4.6363. Min Range: -4.6363

Max Act: 2.7292. Min Act: -0.0000

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 32