Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0004

Data Index: 1568790 (Python Code)

Max Activating Token Index: 167

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0299. Min Act: -0.0004

Data Index: 543082 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0312. Min Act: -0.0004

Data Index: 934977 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0274. Min Act: -0.0004

Data Index: 593009 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0270. Min Act: -0.0004

Data Index: 610889 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0300. Min Act: -0.0004

Data Index: 984505 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1355781 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0258. Min Act: -0.0004

Data Index: 123627 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0294. Min Act: -0.0004

Data Index: 925897 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0299. Min Act: -0.0004

Data Index: 1120511 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0298. Min Act: -0.0004

Data Index: 349148 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0290. Min Act: -0.0004

Data Index: 15548 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0281. Min Act: -0.0004

Data Index: 542761 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1309227 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0256. Min Act: -0.0004

Data Index: 1149095 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0273. Min Act: -0.0004

Data Index: 682511 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1050722 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0240. Min Act: -0.0004

Data Index: 812749 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0258. Min Act: -0.0004

Data Index: 998813 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0249. Min Act: -0.0004

Data Index: 493812 (C4 (Web Text))

Max Activating Token Index: 370