Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3644 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0003

Data Index: 355181 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0527. Min Act: -0.0003

Data Index: 707475 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0530. Min Act: -0.0002

Data Index: 765082 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1003182 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0493. Min Act: -0.0002

Data Index: 48146 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0486. Min Act: -0.0003

Data Index: 55260 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0478. Min Act: -0.0003

Data Index: 888436 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0466. Min Act: -0.0003

Data Index: 999033 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0473. Min Act: -0.0003

Data Index: 396499 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1050411 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0458. Min Act: -0.0002

Data Index: 676255 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0441. Min Act: -0.0003

Data Index: 449581 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0467. Min Act: -0.0003

Data Index: 88591 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0445. Min Act: -0.0002

Data Index: 495130 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0461. Min Act: -0.0003

Data Index: 99237 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0452. Min Act: -0.0002

Data Index: 59598 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0450. Min Act: -0.0002

Data Index: 322440 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0438. Min Act: -0.0003

Data Index: 570086 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0436. Min Act: -0.0003

Data Index: 270840 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1087200 (C4 (Web Text))

Max Activating Token Index: 994