Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 371 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 511347 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1188708 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7042. Min Act: -0.0000

Data Index: 828309 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1173873 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6678. Min Act: -0.0000

Data Index: 437599 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6179. Min Act: -0.0000

Data Index: 895875 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6303. Min Act: -0.0000

Data Index: 344114 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1017572 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1404496 (Python Code)

Max Activating Token Index: 429

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5681. Min Act: -0.0000

Data Index: 673768 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5766. Min Act: -0.0000

Data Index: 199929 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5968. Min Act: -0.0000

Data Index: 943719 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.4612. Min Act: -0.0000

Data Index: 395388 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5490. Min Act: -0.0000

Data Index: 800705 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1336726 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5603. Min Act: -0.0000

Data Index: 621980 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1390305 (Python Code)

Max Activating Token Index: 506

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5320. Min Act: -0.0000

Data Index: 846202 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5462. Min Act: -0.0000

Data Index: 393373 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5279. Min Act: -0.0000

Data Index: 873765 (C4 (Web Text))

Max Activating Token Index: 833