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

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

Neuron 5109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1315515 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1472. Min Act: -0.0000

Data Index: 750696 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1402. Min Act: -0.0000

Data Index: 477815 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1420. Min Act: -0.0000

Data Index: 446917 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1033414 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1359. Min Act: -0.0000

Data Index: 11434 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1146. Min Act: -0.0000

Data Index: 143412 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1576203 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1241. Min Act: -0.0000

Data Index: 499805 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1254364 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1020. Min Act: -0.0000

Data Index: 799849 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1248173 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1088. Min Act: -0.0000

Data Index: 486558 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1048. Min Act: -0.0000

Data Index: 25899 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1105. Min Act: -0.0000

Data Index: 646757 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.0912. Min Act: -0.0000

Data Index: 44128 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1083327 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.0885. Min Act: -0.0000

Data Index: 292231 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1028. Min Act: -0.0000

Data Index: 129997 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1388854 (Python Code)

Max Activating Token Index: 238