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

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

Neuron 1447 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.3243. Min Act: -0.0001

Data Index: 296900 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.3134. Min Act: -0.0001

Data Index: 581267 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2841. Min Act: -0.0001

Data Index: 573757 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2475. Min Act: -0.0001

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2685. Min Act: -0.0001

Data Index: 882120 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2805. Min Act: -0.0001

Data Index: 169882 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2431. Min Act: -0.0001

Data Index: 619036 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2503. Min Act: -0.0001

Data Index: 76666 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1036997 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1240862 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1822. Min Act: -0.0001

Data Index: 943190 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1745. Min Act: -0.0001

Data Index: 920272 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1409200 (Python Code)

Max Activating Token Index: 476

Text #13

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1804. Min Act: -0.0001

Data Index: 571260 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1451162 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1663. Min Act: -0.0001

Data Index: 266075 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1632. Min Act: -0.0001

Data Index: 432253 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1733. Min Act: -0.0001

Data Index: 219709 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1644. Min Act: -0.0001

Data Index: 678861 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.3243. Min Range: -0.3243

Max Act: 0.1516. Min Act: -0.0001

Data Index: 169885 (C4 (Web Text))

Max Activating Token Index: 499