Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1111 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0584. Min Act: -0.0006

Data Index: 189072 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0563. Min Act: -0.0006

Data Index: 356204 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0006

Data Index: 298025 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0581. Min Act: -0.0006

Data Index: 933900 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0579. Min Act: -0.0006

Data Index: 1183455 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0543. Min Act: -0.0006

Data Index: 66120 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0602. Min Act: -0.0006

Data Index: 1197717 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0595. Min Act: -0.0006

Data Index: 522612 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0596. Min Act: -0.0006

Data Index: 1019637 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0575. Min Act: -0.0006

Data Index: 555568 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0508. Min Act: -0.0006

Data Index: 951132 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0585. Min Act: -0.0006

Data Index: 575255 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0527. Min Act: -0.0006

Data Index: 1027780 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0547. Min Act: -0.0006

Data Index: 1295000 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0544. Min Act: -0.0006

Data Index: 152984 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0557. Min Act: -0.0006

Data Index: 1039265 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0588. Min Act: -0.0006

Data Index: 1247181 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0556. Min Act: -0.0006

Data Index: 929333 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0533. Min Act: -0.0006

Data Index: 284531 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0554. Min Act: -0.0006

Data Index: 1235487 (C4 (Web Text))

Max Activating Token Index: 772