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

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

Neuron 1097 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1286069 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0000

Data Index: 509397 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1650875 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1117394 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1442083 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1560601 (Python Code)

Max Activating Token Index: 265

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0379. Min Act: -0.0002

Data Index: 677716 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1338419 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1355045 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1010051 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1468016 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1118808 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1133572 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1086764 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1624401 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0316. Min Act: -0.0001

Data Index: 271191 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1372241 (Python Code)

Max Activating Token Index: 360

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0329. Min Act: -0.0002

Data Index: 658447 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1417468 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0336. Min Act: -0.0000

Data Index: 989475 (C4 (Web Text))

Max Activating Token Index: 894