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

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

Neuron 2451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.6439. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1594201 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1395755 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.6627. Min Act: -0.0000

Data Index: 1417211 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1454630 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.5378. Min Act: -0.0000

Data Index: 377626 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4469. Min Act: -0.0000

Data Index: 402036 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1641871 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1571138 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4183. Min Act: -0.0000

Data Index: 1461770 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4101. Min Act: -0.0000

Data Index: 888292 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1193097 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1654151 (Python Code)

Max Activating Token Index: 820

Text #13

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1484677 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4373. Min Act: -0.0000

Data Index: 721564 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.5017. Min Act: -0.0000

Data Index: 1474219 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1584907 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1379824 (Python Code)

Max Activating Token Index: 266

Text #18

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1493973 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 1.6627. Min Range: -1.6627

Max Act: 1.4732. Min Act: -0.0000

Data Index: 800114 (C4 (Web Text))

Max Activating Token Index: 411