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

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

Neuron 1413 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.5897. Min Act: -0.0000

Data Index: 27401 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.4958. Min Act: -0.0001

Data Index: 1007626 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.2845. Min Act: -0.0001

Data Index: 1424211 (Python Code)

Max Activating Token Index: 914

Text #3

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.1967. Min Act: -0.0001

Data Index: 902475 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1035076 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.2275. Min Act: -0.0001

Data Index: 1098164 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.1235. Min Act: -0.0001

Data Index: 173802 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.1413. Min Act: -0.0001

Data Index: 437626 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0584. Min Act: -0.0001

Data Index: 201796 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0809. Min Act: -0.0001

Data Index: 1386647 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0733. Min Act: -0.0001

Data Index: 1410105 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1077457 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0831. Min Act: -0.0001

Data Index: 1478117 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.1191. Min Act: -0.0001

Data Index: 1652713 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0818. Min Act: -0.0001

Data Index: 1650985 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0674. Min Act: -0.0001

Data Index: 521086 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0375. Min Act: -0.0001

Data Index: 1513992 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0597. Min Act: -0.0001

Data Index: 1581128 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1643523 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 1.5897. Min Range: -1.5897

Max Act: 1.0523. Min Act: -0.0001

Data Index: 871187 (C4 (Web Text))

Max Activating Token Index: 416