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

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

Neuron 3093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.2503. Min Act: -0.0000

Data Index: 644142 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0504. Min Act: -0.0000

Data Index: 300954 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.8447. Min Act: -0.0001

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.9628. Min Act: -0.0001

Data Index: 1599804 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1494987 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.9678. Min Act: -0.0001

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.8808. Min Act: -0.0000

Data Index: 757353 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.8198. Min Act: -0.0000

Data Index: 815510 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1596314 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1383725 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7359. Min Act: -0.0001

Data Index: 1470212 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7412. Min Act: -0.0000

Data Index: 992150 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7296. Min Act: -0.0000

Data Index: 588993 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7144. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7285. Min Act: -0.0001

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.7149. Min Act: -0.0001

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.6581. Min Act: -0.0001

Data Index: 602025 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.6722. Min Act: -0.0000

Data Index: 157376 (C4 (Web Text))

Max Activating Token Index: 327