Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1204 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1664. Min Range: -4.1664

Max Act: 4.1664. Min Act: -0.0000

Data Index: 1057808 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 4.1664. Min Range: -4.1664

Max Act: 4.0372. Min Act: -0.0000

Data Index: 512971 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.6685. Min Act: -0.0000

Data Index: 1293426 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.9212. Min Act: -0.0000

Data Index: 252532 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.9130. Min Act: -0.0000

Data Index: 806308 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.6821. Min Act: -0.0000

Data Index: 262119 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.6397. Min Act: -0.0000

Data Index: 622284 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.4658. Min Act: -0.0000

Data Index: 1145281 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.3469. Min Act: -0.0000

Data Index: 320885 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1820. Min Act: -0.0000

Data Index: 119732 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2794. Min Act: -0.0000

Data Index: 1172665 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2084. Min Act: -0.0000

Data Index: 318979 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1105. Min Act: -0.0000

Data Index: 1150252 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1939. Min Act: -0.0000

Data Index: 334364 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1606. Min Act: -0.0000

Data Index: 837094 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.0100. Min Act: -0.0000

Data Index: 453992 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.0284. Min Act: -0.0000

Data Index: 492831 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.0217. Min Act: -0.0000

Data Index: 755213 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1542. Min Act: -0.0000

Data Index: 191194 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.0167. Min Act: -0.0000

Data Index: 886858 (C4 (Web Text))

Max Activating Token Index: 575