Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 299 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.2052. Min Act: -0.0003

Data Index: 1271589 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1852. Min Act: -0.0003

Data Index: 811343 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1757. Min Act: -0.0003

Data Index: 147504 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1679. Min Act: -0.0003

Data Index: 158948 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1646. Min Act: -0.0003

Data Index: 1055950 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1635. Min Act: -0.0003

Data Index: 443950 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1643. Min Act: -0.0003

Data Index: 272448 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1575. Min Act: -0.0003

Data Index: 1261665 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1604. Min Act: -0.0003

Data Index: 546849 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1639. Min Act: -0.0003

Data Index: 446374 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1615. Min Act: -0.0003

Data Index: 251944 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1540. Min Act: -0.0003

Data Index: 99370 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1612. Min Act: -0.0003

Data Index: 443097 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1537. Min Act: -0.0003

Data Index: 64676 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1553. Min Act: -0.0003

Data Index: 995341 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1546. Min Act: -0.0003

Data Index: 977718 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1516. Min Act: -0.0003

Data Index: 1032284 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1484. Min Act: -0.0003

Data Index: 1155679 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1511. Min Act: -0.0003

Data Index: 1141525 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1482. Min Act: -0.0003

Data Index: 742998 (C4 (Web Text))

Max Activating Token Index: 757