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

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

Neuron 5112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.1063. Min Act: -0.0001

Data Index: 1027417 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0008. Min Act: -0.0001

Data Index: 1305515 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.1340. Min Act: -0.0001

Data Index: 217132 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0939. Min Act: -0.0001

Data Index: 431668 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0460. Min Act: -0.0001

Data Index: 767975 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0622. Min Act: -0.0001

Data Index: 70367 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0511. Min Act: -0.0001

Data Index: 1144738 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0760. Min Act: -0.0001

Data Index: 162968 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0376. Min Act: -0.0001

Data Index: 19280 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0343. Min Act: -0.0001

Data Index: 1238307 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0433. Min Act: -0.0001

Data Index: 631364 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0327. Min Act: -0.0001

Data Index: 458338 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.9373. Min Act: -0.0001

Data Index: 185366 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0227. Min Act: -0.0001

Data Index: 815353 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0499. Min Act: -0.0001

Data Index: 1077598 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0123. Min Act: -0.0001

Data Index: 903630 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.8670. Min Act: -0.0001

Data Index: 804021 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.1340. Min Range: -1.1340

Max Act: 1.0047. Min Act: -0.0001

Data Index: 660915 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.9240. Min Act: -0.0001

Data Index: 326793 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.9484. Min Act: -0.0001

Data Index: 665087 (C4 (Web Text))

Max Activating Token Index: 373