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

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

Neuron 3566 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: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0002

Data Index: 898980 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0538. Min Act: -0.0002

Data Index: 593064 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0449. Min Act: -0.0002

Data Index: 4199 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0405. Min Act: -0.0002

Data Index: 710530 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0448. Min Act: -0.0002

Data Index: 362952 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0487. Min Act: -0.0002

Data Index: 349223 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0535. Min Act: -0.0002

Data Index: 75547 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0496. Min Act: -0.0002

Data Index: 759150 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0363. Min Act: -0.0002

Data Index: 112672 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0419. Min Act: -0.0002

Data Index: 385643 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0493. Min Act: -0.0002

Data Index: 518331 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0526. Min Act: -0.0002

Data Index: 450627 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1010249 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0416. Min Act: -0.0002

Data Index: 876798 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0414. Min Act: -0.0002

Data Index: 791868 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1358674 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0398. Min Act: -0.0002

Data Index: 521442 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1535141 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0264. Min Act: -0.0002

Data Index: 924673 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0386. Min Act: -0.0002

Data Index: 990475 (C4 (Web Text))

Max Activating Token Index: 12