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

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

Neuron 4493 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.8947. Min Act: -0.0000

Data Index: 340220 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.7080. Min Act: -0.0000

Data Index: 1382423 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.6975. Min Act: -0.0000

Data Index: 1534427 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.5961. Min Act: -0.0000

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.5945. Min Act: -0.0000

Data Index: 810879 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.5611. Min Act: -0.0000

Data Index: 1387126 (Python Code)

Max Activating Token Index: 742

Text #6

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.5193. Min Act: -0.0000

Data Index: 1475560 (Python Code)

Max Activating Token Index: 1019

Text #7

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.4415. Min Act: -0.0000

Data Index: 389378 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.3513. Min Act: -0.0000

Data Index: 1503050 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.3230. Min Act: -0.0000

Data Index: 1636807 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.3035. Min Act: -0.0000

Data Index: 1542816 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.4119. Min Act: -0.0000

Data Index: 1391702 (Python Code)

Max Activating Token Index: 172

Text #12

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.4103. Min Act: -0.0000

Data Index: 1167814 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1460899 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.1546. Min Act: -0.0000

Data Index: 1407556 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.2661. Min Act: -0.0000

Data Index: 359543 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.1381. Min Act: -0.0000

Data Index: 810267 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.3653. Min Act: -0.0000

Data Index: 1216590 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.3350. Min Act: -0.0000

Data Index: 1623273 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 2.8947. Min Range: -2.8947

Max Act: 2.3168. Min Act: -0.0000

Data Index: 1397369 (Python Code)

Max Activating Token Index: 27