Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 655 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0005

Data Index: 413851 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0274. Min Act: -0.0006

Data Index: 429373 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0266. Min Act: -0.0005

Data Index: 828985 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1154378 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0281. Min Act: -0.0005

Data Index: 940543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0269. Min Act: -0.0005

Data Index: 861342 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0265. Min Act: -0.0006

Data Index: 915376 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0275. Min Act: -0.0005

Data Index: 865208 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0259. Min Act: -0.0005

Data Index: 935243 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0251. Min Act: -0.0005

Data Index: 496551 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0279. Min Act: -0.0005

Data Index: 65531 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0256. Min Act: -0.0005

Data Index: 238458 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0262. Min Act: -0.0005

Data Index: 380089 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0234. Min Act: -0.0005

Data Index: 1322088 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0255. Min Act: -0.0005

Data Index: 461309 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0271. Min Act: -0.0006

Data Index: 692521 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0271. Min Act: -0.0005

Data Index: 808066 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0254. Min Act: -0.0005

Data Index: 252849 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1303782 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0232. Min Act: -0.0005

Data Index: 294926 (C4 (Web Text))

Max Activating Token Index: 379