Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1447963 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1561814 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1397470 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1545915 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1407436 (Python Code)

Max Activating Token Index: 789

Text #5

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1509624 (Python Code)

Max Activating Token Index: 772

Text #6

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1506573 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2429. Min Act: -0.0000

Data Index: 403060 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2458. Min Act: -0.0000

Data Index: 120958 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2430. Min Act: -0.0001

Data Index: 577477 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2548. Min Act: -0.0001

Data Index: 1552232 (Python Code)

Max Activating Token Index: 748

Text #11

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2428. Min Act: -0.0000

Data Index: 977648 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1105674 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1589027 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1485529 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2243. Min Act: -0.0000

Data Index: 683145 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2272. Min Act: -0.0000

Data Index: 951145 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1365522 (Python Code)

Max Activating Token Index: 680

Text #18

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2216. Min Act: -0.0000

Data Index: 169829 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.3497. Min Range: -0.3497

Max Act: 0.2242. Min Act: -0.0001

Data Index: 72283 (C4 (Web Text))

Max Activating Token Index: 659