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

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

Neuron 4489 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1243. Min Range: -2.1243

Max Act: 2.1243. Min Act: -0.0000

Data Index: 869999 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.9924. Min Act: -0.0000

Data Index: 1053742 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.7638. Min Act: -0.0000

Data Index: 541580 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.7440. Min Act: -0.0000

Data Index: 434674 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.6916. Min Act: -0.0000

Data Index: 938167 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.6232. Min Act: -0.0000

Data Index: 324005 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.6759. Min Act: -0.0000

Data Index: 800443 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.5137. Min Act: -0.0000

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1228395 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.4679. Min Act: -0.0000

Data Index: 472674 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1297975 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1184948 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.3407. Min Act: -0.0000

Data Index: 891311 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1170572 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.2742. Min Act: -0.0000

Data Index: 250036 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.2103. Min Act: -0.0000

Data Index: 327466 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.1322. Min Act: -0.0000

Data Index: 944031 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.1924. Min Act: -0.0000

Data Index: 335825 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.1023. Min Act: -0.0000

Data Index: 491075 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.1243. Min Range: -2.1243

Max Act: 1.0932. Min Act: -0.0000

Data Index: 656374 (C4 (Web Text))

Max Activating Token Index: 220