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

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

Neuron 2160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.7583. Min Act: -0.0000

Data Index: 800696 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.7313. Min Act: -0.0000

Data Index: 800094 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6876. Min Act: -0.0000

Data Index: 249191 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6837. Min Act: 0.0000

Data Index: 399365 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1073919 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1079681 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6440. Min Act: -0.0000

Data Index: 973679 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1221264 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6364. Min Act: -0.0000

Data Index: 943108 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6467. Min Act: -0.0000

Data Index: 38968 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1118323 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6214. Min Act: -0.0000

Data Index: 387203 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6342. Min Act: -0.0000

Data Index: 943764 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6326. Min Act: -0.0000

Data Index: 299167 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1336704 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1115319 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1062278 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6016. Min Act: -0.0000

Data Index: 557798 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6186. Min Act: -0.0000

Data Index: 931092 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.7583. Min Range: -0.7583

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1035896 (C4 (Web Text))

Max Activating Token Index: 875