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

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

Neuron 138 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: 0.1640. Min Range: -0.1640

Max Act: 0.1579. Min Act: -0.0001

Data Index: 472288 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1595. Min Act: -0.0001

Data Index: 854033 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1064414 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1559. Min Act: -0.0002

Data Index: 613384 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0002

Data Index: 751687 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1031229 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1364. Min Act: -0.0001

Data Index: 157539 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1049642 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1221. Min Act: -0.0001

Data Index: 255818 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1194. Min Act: -0.0001

Data Index: 681415 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1159. Min Act: -0.0002

Data Index: 597695 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1318064 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1302. Min Act: -0.0001

Data Index: 699004 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1274. Min Act: -0.0001

Data Index: 340732 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1291136 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1136. Min Act: -0.0001

Data Index: 294449 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1111. Min Act: -0.0002

Data Index: 306580 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1104. Min Act: -0.0002

Data Index: 38860 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1217. Min Act: -0.0001

Data Index: 599018 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1138. Min Act: -0.0001

Data Index: 732980 (C4 (Web Text))

Max Activating Token Index: 311