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

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

Neuron 4328 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0506. Min Range: -3.0506

Max Act: 3.0506. Min Act: -0.0001

Data Index: 526621 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.4515. Min Act: -0.0001

Data Index: 1000132 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.3819. Min Act: -0.0001

Data Index: 529296 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.2558. Min Act: -0.0001

Data Index: 1258745 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.2342. Min Act: -0.0001

Data Index: 476769 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.0150. Min Act: -0.0001

Data Index: 639119 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.2661. Min Act: -0.0001

Data Index: 1277145 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 3.0506. Min Range: -3.0506

Max Act: 1.9404. Min Act: -0.0001

Data Index: 536786 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.0144. Min Act: -0.0001

Data Index: 928916 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.1890. Min Act: -0.0001

Data Index: 329186 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.1855. Min Act: -0.0001

Data Index: 974662 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.1776. Min Act: -0.0001

Data Index: 845826 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.0228. Min Act: -0.0001

Data Index: 880257 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 3.0506. Min Range: -3.0506

Max Act: 1.9402. Min Act: -0.0001

Data Index: 979845 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 3.0506. Min Range: -3.0506

Max Act: 1.8975. Min Act: -0.0001

Data Index: 994540 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.0143. Min Act: -0.0001

Data Index: 751400 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 3.0506. Min Range: -3.0506

Max Act: 1.8698. Min Act: -0.0001

Data Index: 897121 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.0506. Min Range: -3.0506

Max Act: 1.8626. Min Act: -0.0001

Data Index: 1234530 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 3.0506. Min Range: -3.0506

Max Act: 1.9450. Min Act: -0.0001

Data Index: 1283077 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.0506. Min Range: -3.0506

Max Act: 2.0314. Min Act: -0.0001

Data Index: 979537 (C4 (Web Text))

Max Activating Token Index: 871