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

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

Neuron 624 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7377. Min Act: -0.0000

Data Index: 840556 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6346. Min Act: -0.0000

Data Index: 241084 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6101. Min Act: -0.0000

Data Index: 251287 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6083. Min Act: -0.0000

Data Index: 544044 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5951. Min Act: -0.0000

Data Index: 657371 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6006. Min Act: -0.0000

Data Index: 645718 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5996. Min Act: -0.0000

Data Index: 29753 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5774. Min Act: -0.0000

Data Index: 266082 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1321397 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5758. Min Act: -0.0000

Data Index: 445771 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5730. Min Act: -0.0000

Data Index: 356108 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5868. Min Act: -0.0000

Data Index: 689424 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1620684 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5630. Min Act: -0.0000

Data Index: 594362 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1115255 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5448. Min Act: -0.0000

Data Index: 494508 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5396. Min Act: -0.0000

Data Index: 754934 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5234. Min Act: -0.0000

Data Index: 834587 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5345. Min Act: -0.0000

Data Index: 813547 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5179. Min Act: -0.0000

Data Index: 10944 (C4 (Web Text))

Max Activating Token Index: 324