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

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

Neuron 3538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1531925 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1458468 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1610239 (Python Code)

Max Activating Token Index: 666

Text #3

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1389753 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1527014 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1587146 (Python Code)

Max Activating Token Index: 260

Text #6

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1569891 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1130233 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1592669 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2508. Min Act: -0.0000

Data Index: 518362 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1497232 (Python Code)

Max Activating Token Index: 404

Text #11

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2323. Min Act: -0.0000

Data Index: 347243 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1557592 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1363100 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1381598 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1497603 (Python Code)

Max Activating Token Index: 768

Text #16

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1591863 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1534417 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1629404 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1537286 (Python Code)

Max Activating Token Index: 819