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

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

Neuron 2821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3348. Min Act: -0.0001

Data Index: 1179596 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.3088. Min Act: -0.0001

Data Index: 481510 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2602. Min Act: -0.0001

Data Index: 815014 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1121091 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2498. Min Act: -0.0001

Data Index: 369272 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2759. Min Act: -0.0001

Data Index: 164523 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2699. Min Act: -0.0000

Data Index: 589811 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2473. Min Act: -0.0001

Data Index: 902633 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2502. Min Act: -0.0000

Data Index: 868495 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2299. Min Act: -0.0000

Data Index: 466890 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2569. Min Act: -0.0001

Data Index: 517355 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2428. Min Act: -0.0000

Data Index: 614415 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2224. Min Act: -0.0001

Data Index: 945346 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2345. Min Act: -0.0001

Data Index: 778879 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2168. Min Act: -0.0001

Data Index: 718473 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2494. Min Act: -0.0000

Data Index: 884246 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2266. Min Act: -0.0000

Data Index: 130800 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2235. Min Act: -0.0001

Data Index: 1321199 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2557. Min Act: -0.0000

Data Index: 768107 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.3348. Min Range: -0.3348

Max Act: 0.2382. Min Act: -0.0000

Data Index: 309547 (C4 (Web Text))

Max Activating Token Index: 388