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

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

Neuron 547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0575. Min Act: -0.0001

Data Index: 145208 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1342708 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1274155 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1598241 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1387573 (Python Code)

Max Activating Token Index: 271

Text #5

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0371. Min Act: -0.0001

Data Index: 528654 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1442677 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0371. Min Act: -0.0002

Data Index: 187629 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1641892 (Python Code)

Max Activating Token Index: 767

Text #9

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0341. Min Act: -0.0001

Data Index: 469152 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0317. Min Act: -0.0001

Data Index: 355969 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0355. Min Act: -0.0001

Data Index: 318140 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1185603 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1408982 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1257451 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0321. Min Act: -0.0001

Data Index: 881972 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1485435 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1055657 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1528055 (Python Code)

Max Activating Token Index: 589