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

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

Neuron 1663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1120788 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1308567 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2332. Min Act: -0.0000

Data Index: 121878 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1197546 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2348. Min Act: -0.0001

Data Index: 1247241 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2329. Min Act: -0.0000

Data Index: 214808 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2124. Min Act: -0.0000

Data Index: 712538 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2224. Min Act: -0.0001

Data Index: 146298 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2115. Min Act: -0.0000

Data Index: 322689 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1133119 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2055. Min Act: -0.0000

Data Index: 745526 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1964. Min Act: -0.0001

Data Index: 932083 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2015. Min Act: -0.0001

Data Index: 308478 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1255239 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2032. Min Act: -0.0000

Data Index: 595909 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2005. Min Act: -0.0000

Data Index: 54879 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1943. Min Act: -0.0001

Data Index: 120319 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1942. Min Act: -0.0000

Data Index: 330703 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1044513 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1318475 (C4 (Web Text))

Max Activating Token Index: 661