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

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

Neuron 1526 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3439. Min Act: -0.0000

Data Index: 382242 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1113587 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1155522 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1585150 (Python Code)

Max Activating Token Index: 205

Text #4

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1004998 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2973. Min Act: -0.0000

Data Index: 704019 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2740. Min Act: -0.0000

Data Index: 769135 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2823. Min Act: -0.0000

Data Index: 473527 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2719. Min Act: -0.0000

Data Index: 158678 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1068149 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2744. Min Act: -0.0000

Data Index: 645007 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2639. Min Act: -0.0000

Data Index: 190457 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2701. Min Act: -0.0000

Data Index: 622543 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1279713 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2530. Min Act: -0.0000

Data Index: 577982 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1167485 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1316826 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2464. Min Act: -0.0000

Data Index: 632700 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2360. Min Act: -0.0000

Data Index: 422697 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2417. Min Act: -0.0001

Data Index: 538533 (C4 (Web Text))

Max Activating Token Index: 172