Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3257. Min Act: -0.0001

Data Index: 267598 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.3060. Min Act: -0.0001

Data Index: 736279 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2744. Min Act: -0.0001

Data Index: 354840 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1043855 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2313. Min Act: -0.0001

Data Index: 312715 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2205. Min Act: -0.0001

Data Index: 867029 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2295. Min Act: -0.0001

Data Index: 81173 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2172. Min Act: -0.0001

Data Index: 1364982 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2176. Min Act: -0.0001

Data Index: 575996 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2169. Min Act: -0.0001

Data Index: 784628 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1223038 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2163. Min Act: -0.0001

Data Index: 699883 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2085. Min Act: -0.0001

Data Index: 728028 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2075. Min Act: -0.0001

Data Index: 628516 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2131. Min Act: -0.0001

Data Index: 876925 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1008422 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2112. Min Act: -0.0001

Data Index: 267393 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2099. Min Act: -0.0001

Data Index: 1224572 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.2084. Min Act: -0.0001

Data Index: 164458 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.3257. Min Range: -0.3257

Max Act: 0.1998. Min Act: -0.0001

Data Index: 795168 (C4 (Web Text))

Max Activating Token Index: 674