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

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

Neuron 4794 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1531472 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1586606 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1461598 (Python Code)

Max Activating Token Index: 577

Text #3

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1538853 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1564645 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1416868 (Python Code)

Max Activating Token Index: 126

Text #6

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1482201 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1383557 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1538071 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1533681 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1610982 (Python Code)

Max Activating Token Index: 406

Text #11

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1408930 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1512226 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1528909 (Python Code)

Max Activating Token Index: 904

Text #14

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0991. Min Act: -0.0000

Data Index: 768609 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1400228 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1561822 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1497055 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1482418 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1565117 (Python Code)

Max Activating Token Index: 304