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

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

Neuron 4150 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9486. Min Act: -0.0000

Data Index: 304394 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8799. Min Act: -0.0000

Data Index: 953757 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1160031 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1306167 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9003. Min Act: -0.0000

Data Index: 344924 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8999. Min Act: -0.0000

Data Index: 446474 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8906. Min Act: -0.0000

Data Index: 965998 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1326519 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8638. Min Act: -0.0000

Data Index: 178787 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1030452 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8579. Min Act: -0.0000

Data Index: 996388 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8068. Min Act: -0.0000

Data Index: 919847 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1316281 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.7958. Min Act: -0.0000

Data Index: 125019 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8995. Min Act: -0.0000

Data Index: 407468 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8131. Min Act: -0.0000

Data Index: 33855 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8461. Min Act: -0.0000

Data Index: 698712 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1189578 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8480. Min Act: -0.0000

Data Index: 236663 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8087. Min Act: -0.0000

Data Index: 150226 (C4 (Web Text))

Max Activating Token Index: 465