Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 43 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1087219 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1261821 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1013453 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2527. Min Act: -0.0000

Data Index: 679269 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2588. Min Act: 0.0000

Data Index: 702461 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1292035 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2467. Min Act: -0.0000

Data Index: 888467 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1327356 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2443. Min Act: -0.0000

Data Index: 807032 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1065295 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1096601 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1273193 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2490. Min Act: -0.0000

Data Index: 856203 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1548015 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1231268 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1485228 (Python Code)

Max Activating Token Index: 469

Text #16

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2323. Min Act: -0.0000

Data Index: 262504 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1586701 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1656019 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2149. Min Act: -0.0000

Data Index: 695325 (C4 (Web Text))

Max Activating Token Index: 420