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

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

Neuron 3799 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1169733 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.3162. Min Act: -0.0000

Data Index: 151908 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2864. Min Act: -0.0000

Data Index: 134289 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2831. Min Act: -0.0000

Data Index: 813107 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2856. Min Act: -0.0000

Data Index: 206997 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1284549 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2751. Min Act: -0.0000

Data Index: 287835 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2736. Min Act: -0.0000

Data Index: 233728 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2590. Min Act: -0.0000

Data Index: 320852 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2466. Min Act: 0.0000

Data Index: 500196 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2628. Min Act: 0.0000

Data Index: 379445 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2358. Min Act: -0.0000

Data Index: 675836 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1075887 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2365. Min Act: -0.0000

Data Index: 231654 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1159838 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2347. Min Act: -0.0000

Data Index: 472930 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2247. Min Act: -0.0000

Data Index: 167097 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2216. Min Act: -0.0000

Data Index: 296822 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2245. Min Act: -0.0000

Data Index: 570035 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.3193. Min Range: -0.3193

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1242454 (C4 (Web Text))

Max Activating Token Index: 71