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

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

Neuron 442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9756. Min Range: -4.9756

Max Act: 4.9756. Min Act: -0.0000

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 4.9756. Min Range: -4.9756

Max Act: 4.2483. Min Act: -0.0000

Data Index: 381810 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.9962. Min Act: -0.0000

Data Index: 923468 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 4.9756. Min Range: -4.9756

Max Act: 4.0072. Min Act: -0.0000

Data Index: 132882 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.6561. Min Act: -0.0000

Data Index: 1179377 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 4.9756. Min Range: -4.9756

Max Act: 4.4137. Min Act: -0.0000

Data Index: 1020824 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.6954. Min Act: -0.0000

Data Index: 799706 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.4843. Min Act: -0.0000

Data Index: 1174192 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.4218. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.3324. Min Act: -0.0000

Data Index: 356975 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.3162. Min Act: -0.0000

Data Index: 795674 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1047021 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.2198. Min Act: -0.0000

Data Index: 1398474 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.3783. Min Act: -0.0000

Data Index: 1160311 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 4.9756. Min Range: -4.9756

Max Act: 4.2813. Min Act: -0.0000

Data Index: 1262660 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.2167. Min Act: -0.0000

Data Index: 1616886 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 4.9756. Min Range: -4.9756

Max Act: 3.1305. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 4.9756. Min Range: -4.9756

Max Act: 2.7510. Min Act: -0.0000

Data Index: 555866 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 4.9756. Min Range: -4.9756

Max Act: 2.4785. Min Act: -0.0000

Data Index: 116819 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 4.9756. Min Range: -4.9756

Max Act: 2.9636. Min Act: -0.0000

Data Index: 316950 (C4 (Web Text))

Max Activating Token Index: 121