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

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

Neuron 1515 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.2214. Min Act: -0.0002

Data Index: 768129 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1981. Min Act: -0.0002

Data Index: 1076316 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1973. Min Act: -0.0002

Data Index: 93702 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1657. Min Act: -0.0002

Data Index: 1352226 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1755. Min Act: -0.0002

Data Index: 780729 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1737. Min Act: -0.0002

Data Index: 279590 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1655. Min Act: -0.0002

Data Index: 358969 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1640. Min Act: -0.0002

Data Index: 266967 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1683. Min Act: -0.0002

Data Index: 762655 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1683. Min Act: -0.0002

Data Index: 1162990 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1707. Min Act: -0.0002

Data Index: 450791 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1610. Min Act: -0.0002

Data Index: 62151 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1076330 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1586. Min Act: -0.0002

Data Index: 932618 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1572. Min Act: -0.0002

Data Index: 206347 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1672. Min Act: -0.0002

Data Index: 113933 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1553. Min Act: -0.0002

Data Index: 65577 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1188068 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1495. Min Act: -0.0002

Data Index: 362834 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1508. Min Act: -0.0002

Data Index: 96352 (C4 (Web Text))

Max Activating Token Index: 820