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

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

Neuron 3765 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: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0001

Data Index: 397769 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2687. Min Act: -0.0001

Data Index: 796660 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2571. Min Act: -0.0001

Data Index: 361998 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1307779 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1228390 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2428. Min Act: -0.0001

Data Index: 716992 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1060401 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2435. Min Act: -0.0001

Data Index: 598837 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2502. Min Act: -0.0001

Data Index: 946622 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2409. Min Act: -0.0001

Data Index: 241582 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2375. Min Act: -0.0001

Data Index: 933592 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2343. Min Act: -0.0001

Data Index: 787528 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1344003 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2349. Min Act: -0.0001

Data Index: 70544 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2343. Min Act: -0.0001

Data Index: 247410 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2347. Min Act: -0.0001

Data Index: 681695 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2330. Min Act: -0.0001

Data Index: 442742 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2314. Min Act: -0.0001

Data Index: 1311504 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2291. Min Act: -0.0001

Data Index: 52783 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2356. Min Act: -0.0001

Data Index: 670659 (C4 (Web Text))

Max Activating Token Index: 495