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

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

Neuron 310 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.8290. Min Act: -0.0000

Data Index: 1179283 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.4934. Min Act: -0.0000

Data Index: 601571 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.3475. Min Act: -0.0000

Data Index: 226099 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1790. Min Act: -0.0000

Data Index: 942618 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1187768 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1557. Min Act: -0.0000

Data Index: 64965 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.2324. Min Act: -0.0000

Data Index: 40256 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1404. Min Act: -0.0000

Data Index: 75676 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1259488 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.0621. Min Act: -0.0000

Data Index: 511377 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.2057. Min Act: -0.0000

Data Index: 285117 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1539. Min Act: -0.0000

Data Index: 59008 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.0884. Min Act: -0.0000

Data Index: 579055 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.1315. Min Act: -0.0000

Data Index: 1284163 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.0013. Min Act: -0.0000

Data Index: 531340 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 2.8290. Min Range: -2.8290

Max Act: 0.9490. Min Act: -0.0000

Data Index: 232905 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.0047. Min Act: -0.0000

Data Index: 518891 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.8290. Min Range: -2.8290

Max Act: 0.9480. Min Act: -0.0000

Data Index: 746427 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 2.8290. Min Range: -2.8290

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1181596 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 2.8290. Min Range: -2.8290

Max Act: 0.9743. Min Act: -0.0000

Data Index: 77755 (C4 (Web Text))

Max Activating Token Index: 928