Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0006

Data Index: 545106 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1014749 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0438. Min Act: -0.0006

Data Index: 36973 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1296547 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0407. Min Act: -0.0006

Data Index: 1291507 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1121243 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1299333 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0364. Min Act: -0.0006

Data Index: 795174 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1117683 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0363. Min Act: -0.0006

Data Index: 920606 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0361. Min Act: -0.0006

Data Index: 291 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0345. Min Act: -0.0006

Data Index: 85977 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0364. Min Act: -0.0006

Data Index: 597796 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0333. Min Act: -0.0006

Data Index: 22582 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1303425 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0346. Min Act: -0.0006

Data Index: 444164 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1068901 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0344. Min Act: -0.0006

Data Index: 120240 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0332. Min Act: -0.0006

Data Index: 851051 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0338. Min Act: -0.0006

Data Index: 574823 (C4 (Web Text))

Max Activating Token Index: 681