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

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

Neuron 299 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: 0.3573. Min Range: -0.3573

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1205504 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3152. Min Act: -0.0000

Data Index: 313572 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2811. Min Act: -0.0000

Data Index: 961609 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2795. Min Act: -0.0000

Data Index: 800839 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2740. Min Act: -0.0000

Data Index: 888876 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2651. Min Act: -0.0000

Data Index: 492452 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2843. Min Act: -0.0000

Data Index: 379627 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2696. Min Act: -0.0000

Data Index: 310964 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2523. Min Act: -0.0000

Data Index: 686038 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1036326 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2536. Min Act: -0.0000

Data Index: 548692 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2514. Min Act: -0.0000

Data Index: 105356 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1038923 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1029356 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2446. Min Act: -0.0000

Data Index: 8316 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2432. Min Act: -0.0000

Data Index: 304903 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2393. Min Act: -0.0000

Data Index: 513697 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2446. Min Act: -0.0000

Data Index: 388978 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2300. Min Act: -0.0000

Data Index: 143109 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2374. Min Act: -0.0000

Data Index: 158732 (C4 (Web Text))

Max Activating Token Index: 46