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

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

Neuron 5856 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: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1135145 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0623. Min Act: -0.0002

Data Index: 496622 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0582. Min Act: -0.0002

Data Index: 58249 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0604. Min Act: -0.0002

Data Index: 44842 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0560. Min Act: -0.0002

Data Index: 717082 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0533. Min Act: -0.0002

Data Index: 565215 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0551. Min Act: -0.0002

Data Index: 552846 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0528. Min Act: -0.0002

Data Index: 687003 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0527. Min Act: -0.0002

Data Index: 393434 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1179340 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0542. Min Act: -0.0002

Data Index: 438637 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0509. Min Act: -0.0002

Data Index: 278565 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0493. Min Act: -0.0002

Data Index: 41549 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0463. Min Act: -0.0002

Data Index: 98354 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1121085 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1166378 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0470. Min Act: -0.0002

Data Index: 992169 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1148133 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1102257 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0450. Min Act: -0.0002

Data Index: 440567 (C4 (Web Text))

Max Activating Token Index: 401