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

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

Neuron 4003 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: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1086933 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0468. Min Act: -0.0002

Data Index: 373256 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0449. Min Act: -0.0002

Data Index: 440384 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1329505 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0451. Min Act: -0.0002

Data Index: 55378 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1653757 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1520324 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1457254 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1087039 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0444. Min Act: -0.0002

Data Index: 389932 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1565322 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1366899 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1457772 (Python Code)

Max Activating Token Index: 577

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1463524 (Python Code)

Max Activating Token Index: 626

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1579133 (Python Code)

Max Activating Token Index: 946

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1552095 (Python Code)

Max Activating Token Index: 972

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1399710 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1113789 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1395657 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0418. Min Act: -0.0002

Data Index: 606420 (C4 (Web Text))

Max Activating Token Index: 17