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

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

Neuron 2037 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2444. Min Act: -0.0002

Data Index: 1146519 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2083. Min Act: -0.0002

Data Index: 470852 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.1649. Min Act: -0.0002

Data Index: 194341 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2214. Min Act: -0.0002

Data Index: 1133959 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.2127. Min Act: -0.0002

Data Index: 212189 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0741. Min Act: -0.0001

Data Index: 1238721 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0970. Min Act: -0.0002

Data Index: 1203662 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0098. Min Act: -0.0002

Data Index: 281293 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0332. Min Act: -0.0002

Data Index: 273196 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0127. Min Act: -0.0001

Data Index: 360467 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0138. Min Act: -0.0002

Data Index: 1219572 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0358. Min Act: -0.0001

Data Index: 262953 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.2444. Min Range: -1.2444

Max Act: 1.0339. Min Act: -0.0002

Data Index: 1323015 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9344. Min Act: -0.0002

Data Index: 34092 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9564. Min Act: -0.0001

Data Index: 566142 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9735. Min Act: -0.0001

Data Index: 197416 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9558. Min Act: -0.0001

Data Index: 781325 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9712. Min Act: -0.0002

Data Index: 1122799 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9666. Min Act: -0.0002

Data Index: 682636 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.2444. Min Range: -1.2444

Max Act: 0.9271. Min Act: -0.0002

Data Index: 45953 (C4 (Web Text))

Max Activating Token Index: 435