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

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

Neuron 379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2582. Min Act: -0.0001

Data Index: 914111 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2686. Min Act: -0.0000

Data Index: 872077 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2621. Min Act: -0.0000

Data Index: 766228 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2511. Min Act: -0.0000

Data Index: 735870 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2490. Min Act: -0.0000

Data Index: 236453 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2460. Min Act: -0.0000

Data Index: 406301 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1087780 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2497. Min Act: -0.0000

Data Index: 621705 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1074282 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1441186 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1091722 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2411. Min Act: -0.0000

Data Index: 292723 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1031053 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2251. Min Act: -0.0000

Data Index: 90528 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2323. Min Act: -0.0000

Data Index: 56963 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2209. Min Act: -0.0000

Data Index: 665776 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1004561 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1432903 (Python Code)

Max Activating Token Index: 631

Text #18

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2295. Min Act: -0.0000

Data Index: 377786 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1015360 (C4 (Web Text))

Max Activating Token Index: 520