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

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

Neuron 4194 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 696090 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 258021 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 559049 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1243222 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 859043 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 471696 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1258896 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1607111 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1355875 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 14166 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 660958 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1148847 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1267700 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 929327 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 206239 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 77425 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1293823 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 60716 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 715688 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1143380 (C4 (Web Text))

Max Activating Token Index: 653