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

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

Neuron 3660 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0177. Min Range: -1.0177

Max Act: 1.0177. Min Act: -0.0001

Data Index: 49014 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.0177. Min Range: -1.0177

Max Act: 1.0173. Min Act: -0.0001

Data Index: 438642 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1568759 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9554. Min Act: -0.0001

Data Index: 90707 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9747. Min Act: -0.0001

Data Index: 1280043 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1159860 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8405. Min Act: -0.0001

Data Index: 1356386 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1165070 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8344. Min Act: -0.0001

Data Index: 354427 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8210. Min Act: -0.0001

Data Index: 1417950 (Python Code)

Max Activating Token Index: 354

Text #10

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1502947 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8345. Min Act: -0.0001

Data Index: 914533 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8555. Min Act: -0.0001

Data Index: 339654 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8615. Min Act: -0.0001

Data Index: 436223 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7925. Min Act: -0.0001

Data Index: 934409 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1412481 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7850. Min Act: -0.0001

Data Index: 842317 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7997. Min Act: -0.0001

Data Index: 1083378 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7646. Min Act: -0.0001

Data Index: 1229271 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8287. Min Act: -0.0001

Data Index: 280317 (C4 (Web Text))

Max Activating Token Index: 900