Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3895 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1663. Min Act: -0.0001

Data Index: 880822 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1801. Min Act: -0.0001

Data Index: 648051 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1154598 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1724. Min Act: -0.0001

Data Index: 971567 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1750. Min Act: -0.0001

Data Index: 111514 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1062707 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1102865 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1279598 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1498. Min Act: -0.0001

Data Index: 693013 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1281. Min Act: -0.0001

Data Index: 553036 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1038456 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1329732 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1318. Min Act: -0.0001

Data Index: 521913 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1297. Min Act: -0.0001

Data Index: 392678 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1112657 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1295. Min Act: -0.0000

Data Index: 717865 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1236. Min Act: -0.0000

Data Index: 471225 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1178. Min Act: -0.0001

Data Index: 310363 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1087930 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1259. Min Act: -0.0001

Data Index: 539991 (C4 (Web Text))

Max Activating Token Index: 629