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

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

Neuron 2106 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.4744. Min Act: -0.0003

Data Index: 472018 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.4213. Min Act: -0.0003

Data Index: 1061015 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.4282. Min Act: -0.0003

Data Index: 75121 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.2807. Min Act: -0.0003

Data Index: 487358 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1795. Min Act: -0.0003

Data Index: 138937 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1385. Min Act: -0.0003

Data Index: 1105538 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0677. Min Act: -0.0003

Data Index: 834751 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1252. Min Act: -0.0003

Data Index: 319131 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1871. Min Act: -0.0003

Data Index: 905176 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1240. Min Act: -0.0003

Data Index: 228399 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0195. Min Act: -0.0003

Data Index: 340320 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0925. Min Act: -0.0003

Data Index: 873839 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.4744. Min Range: -1.4744

Max Act: 0.9935. Min Act: -0.0003

Data Index: 161457 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0234. Min Act: -0.0003

Data Index: 761532 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0382. Min Act: -0.0003

Data Index: 1306714 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1002. Min Act: -0.0003

Data Index: 1196075 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.1670. Min Act: -0.0003

Data Index: 548657 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0049. Min Act: -0.0003

Data Index: 451206 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0024. Min Act: -0.0003

Data Index: 344031 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.4744. Min Range: -1.4744

Max Act: 1.0539. Min Act: -0.0003

Data Index: 776648 (C4 (Web Text))

Max Activating Token Index: 5