Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3599 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0002

Data Index: 460884 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0578. Min Act: -0.0001

Data Index: 420384 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0543. Min Act: -0.0001

Data Index: 382265 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0523. Min Act: -0.0002

Data Index: 852806 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0538. Min Act: -0.0001

Data Index: 928303 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0499. Min Act: -0.0001

Data Index: 541562 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0535. Min Act: -0.0002

Data Index: 589293 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0507. Min Act: -0.0002

Data Index: 85 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0515. Min Act: -0.0002

Data Index: 853846 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0499. Min Act: -0.0001

Data Index: 536761 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0535. Min Act: -0.0001

Data Index: 971801 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0494. Min Act: -0.0001

Data Index: 70548 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0507. Min Act: -0.0001

Data Index: 993427 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0503. Min Act: -0.0002

Data Index: 60080 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0509. Min Act: -0.0001

Data Index: 595353 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1037081 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0487. Min Act: -0.0002

Data Index: 612285 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0481. Min Act: -0.0002

Data Index: 241941 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0479. Min Act: -0.0002

Data Index: 588879 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1034279 (C4 (Web Text))

Max Activating Token Index: 92