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

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

Neuron 1347 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.7434. Min Act: -0.0001

Data Index: 93994 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1794. Min Act: -0.0001

Data Index: 466627 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.2078. Min Act: -0.0001

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1521. Min Act: -0.0001

Data Index: 606830 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1208. Min Act: -0.0001

Data Index: 1270520 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1292. Min Act: -0.0001

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.2274. Min Act: -0.0001

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.0967. Min Act: -0.0001

Data Index: 757814 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1061. Min Act: -0.0001

Data Index: 546229 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1175. Min Act: -0.0001

Data Index: 896920 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.0776. Min Act: -0.0001

Data Index: 6820 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.0293. Min Act: -0.0001

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.0204. Min Act: -0.0001

Data Index: 1474700 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.1266. Min Act: -0.0001

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.7434. Min Range: -1.7434

Max Act: 0.9883. Min Act: -0.0001

Data Index: 1372938 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 1.7434. Min Range: -1.7434

Max Act: 1.0065. Min Act: -0.0001

Data Index: 1622763 (Python Code)

Max Activating Token Index: 783

Text #16

Max Range: 1.7434. Min Range: -1.7434

Max Act: 0.9259. Min Act: -0.0001

Data Index: 1256796 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.7434. Min Range: -1.7434

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1147380 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.7434. Min Range: -1.7434

Max Act: 0.9975. Min Act: -0.0001

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 1.7434. Min Range: -1.7434

Max Act: 0.9951. Min Act: -0.0001

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 1022