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

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

Neuron 2082 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.4326. Min Act: -0.0001

Data Index: 689026 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.3707. Min Act: -0.0001

Data Index: 1047089 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.3409. Min Act: -0.0001

Data Index: 480181 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.2887. Min Act: -0.0001

Data Index: 32894 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.2236. Min Act: -0.0001

Data Index: 314258 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.1866. Min Act: -0.0001

Data Index: 365923 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.2618. Min Act: -0.0001

Data Index: 1318843 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.1253. Min Act: -0.0001

Data Index: 564267 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0691. Min Act: -0.0001

Data Index: 896753 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.1765. Min Act: -0.0001

Data Index: 595465 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0603. Min Act: -0.0001

Data Index: 952582 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0284. Min Act: -0.0001

Data Index: 493188 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.1226. Min Act: -0.0001

Data Index: 1031744 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0911. Min Act: -0.0001

Data Index: 950898 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.1169. Min Act: -0.0001

Data Index: 243209 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0773. Min Act: -0.0001

Data Index: 228942 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0588. Min Act: -0.0001

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.1118. Min Act: -0.0001

Data Index: 641259 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0110. Min Act: -0.0001

Data Index: 528737 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.4326. Min Range: -1.4326

Max Act: 1.0126. Min Act: -0.0001

Data Index: 364226 (C4 (Web Text))

Max Activating Token Index: 178