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

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

Neuron 4929 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.8738. Min Act: -0.0003

Data Index: 805422 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.8612. Min Act: -0.0002

Data Index: 28898 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.8087. Min Act: -0.0002

Data Index: 226071 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.7958. Min Act: -0.0002

Data Index: 440070 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.6599. Min Act: -0.0002

Data Index: 611035 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.7260. Min Act: -0.0002

Data Index: 1359445 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.4575. Min Act: -0.0002

Data Index: 411730 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.4857. Min Act: -0.0002

Data Index: 19223 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5943. Min Act: -0.0002

Data Index: 553911 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.4512. Min Act: -0.0003

Data Index: 1285587 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5765. Min Act: -0.0002

Data Index: 1294578 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5673. Min Act: -0.0002

Data Index: 554514 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.4369. Min Act: -0.0002

Data Index: 1284479 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5649. Min Act: -0.0003

Data Index: 938794 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.7020. Min Act: -0.0003

Data Index: 203270 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5606. Min Act: -0.0003

Data Index: 934101 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5586. Min Act: -0.0002

Data Index: 1103726 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.4001. Min Act: -0.0002

Data Index: 939512 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5496. Min Act: -0.0002

Data Index: 1133283 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 7.8738. Min Range: -7.8738

Max Act: 7.5200. Min Act: -0.0002

Data Index: 639140 (C4 (Web Text))

Max Activating Token Index: 360