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

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

Neuron 514 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: 0.2664. Min Range: -0.2664

Max Act: 0.2664. Min Act: -0.0001

Data Index: 449615 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2565. Min Act: -0.0000

Data Index: 141517 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1014039 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2529. Min Act: -0.0001

Data Index: 54806 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2306. Min Act: -0.0000

Data Index: 635989 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1192332 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1270706 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1024124 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2231. Min Act: -0.0000

Data Index: 248420 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2352. Min Act: -0.0000

Data Index: 894126 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2207. Min Act: -0.0000

Data Index: 148609 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2169. Min Act: -0.0000

Data Index: 995309 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2153. Min Act: -0.0000

Data Index: 385782 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2224. Min Act: -0.0000

Data Index: 37920 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2206. Min Act: -0.0001

Data Index: 426776 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2193. Min Act: -0.0000

Data Index: 675717 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2251. Min Act: -0.0001

Data Index: 608878 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1094150 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2094. Min Act: -0.0000

Data Index: 177132 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2155. Min Act: -0.0000

Data Index: 723324 (C4 (Web Text))

Max Activating Token Index: 1011