Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1336 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0000

Data Index: 88532 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4855. Min Act: -0.0000

Data Index: 279085 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4913. Min Act: -0.0000

Data Index: 132037 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4031. Min Act: -0.0000

Data Index: 98413 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3218. Min Act: -0.0000

Data Index: 936320 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3019. Min Act: -0.0000

Data Index: 1060832 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2161. Min Act: -0.0000

Data Index: 488615 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2751. Min Act: -0.0000

Data Index: 857238 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1193100 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1221263 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2984. Min Act: -0.0000

Data Index: 723260 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1280924 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1965. Min Act: -0.0000

Data Index: 793210 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1282. Min Act: -0.0000

Data Index: 456011 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1103335 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1628. Min Act: -0.0000

Data Index: 946411 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1294059 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1516. Min Act: -0.0000

Data Index: 439062 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0772. Min Act: -0.0000

Data Index: 475030 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1536. Min Act: -0.0000

Data Index: 546810 (C4 (Web Text))

Max Activating Token Index: 337