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

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

Neuron 5482 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0002

Data Index: 908186 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1193032 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0553. Min Act: -0.0002

Data Index: 11417 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0582. Min Act: -0.0002

Data Index: 128788 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0587. Min Act: -0.0002

Data Index: 366190 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1054951 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0530. Min Act: -0.0002

Data Index: 570354 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0535. Min Act: -0.0002

Data Index: 371577 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0534. Min Act: -0.0002

Data Index: 492456 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1208325 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0524. Min Act: -0.0002

Data Index: 399115 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1013136 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0512. Min Act: -0.0002

Data Index: 192411 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0490. Min Act: -0.0002

Data Index: 600003 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0509. Min Act: -0.0002

Data Index: 377425 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1330773 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0471. Min Act: -0.0002

Data Index: 168388 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0488. Min Act: -0.0002

Data Index: 206750 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0517. Min Act: -0.0002

Data Index: 41808 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0485. Min Act: -0.0002

Data Index: 238098 (C4 (Web Text))

Max Activating Token Index: 201