Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2550 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0519. Min Act: -0.0004

Data Index: 198600 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0004

Data Index: 451689 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0523. Min Act: -0.0004

Data Index: 253467 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0501. Min Act: -0.0004

Data Index: 1149596 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0487. Min Act: -0.0004

Data Index: 669456 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0471. Min Act: -0.0004

Data Index: 159956 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0468. Min Act: -0.0004

Data Index: 315452 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0483. Min Act: -0.0004

Data Index: 1318369 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0446. Min Act: -0.0004

Data Index: 301508 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0448. Min Act: -0.0004

Data Index: 1009733 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0457. Min Act: -0.0004

Data Index: 777895 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0429. Min Act: -0.0004

Data Index: 16961 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0465. Min Act: -0.0004

Data Index: 581265 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0444. Min Act: -0.0004

Data Index: 1253349 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0439. Min Act: -0.0004

Data Index: 527606 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0409. Min Act: -0.0004

Data Index: 409952 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0427. Min Act: -0.0004

Data Index: 358927 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0431. Min Act: -0.0004

Data Index: 233278 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0397. Min Act: -0.0004

Data Index: 1252282 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0416. Min Act: -0.0004

Data Index: 976185 (C4 (Web Text))

Max Activating Token Index: 880