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

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

Neuron 5805 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7650. Min Act: 0.0000

Data Index: 1325304 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.7140. Min Act: -0.0000

Data Index: 585602 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.5783. Min Act: -0.0000

Data Index: 485541 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6223. Min Act: -0.0000

Data Index: 459199 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6352. Min Act: -0.0000

Data Index: 94843 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.6194. Min Act: -0.0000

Data Index: 156426 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.5612. Min Act: -0.0000

Data Index: 8118 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.5276. Min Act: -0.0000

Data Index: 911982 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4284. Min Act: -0.0000

Data Index: 360761 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4919. Min Act: -0.0000

Data Index: 577100 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.5917. Min Act: -0.0000

Data Index: 665007 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1102762 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.5699. Min Act: -0.0000

Data Index: 962564 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.3733. Min Act: -0.0000

Data Index: 902503 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4564. Min Act: -0.0000

Data Index: 660749 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1148225 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4293. Min Act: -0.0000

Data Index: 817339 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4322. Min Act: -0.0000

Data Index: 322970 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4162. Min Act: -0.0000

Data Index: 467823 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.7650. Min Range: -1.7650

Max Act: 1.4013. Min Act: -0.0000

Data Index: 925674 (C4 (Web Text))

Max Activating Token Index: 235