Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1579 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0006

Data Index: 645912 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0728. Min Act: -0.0006

Data Index: 188319 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0638. Min Act: -0.0006

Data Index: 575937 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0628. Min Act: -0.0006

Data Index: 792890 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0535. Min Act: -0.0006

Data Index: 136073 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0451. Min Act: -0.0006

Data Index: 766450 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0433. Min Act: -0.0006

Data Index: 283418 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0387. Min Act: -0.0006

Data Index: 454175 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0395. Min Act: -0.0006

Data Index: 948613 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0400. Min Act: -0.0006

Data Index: 158996 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0391. Min Act: -0.0006

Data Index: 567101 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0401. Min Act: -0.0005

Data Index: 451412 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1207889 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0367. Min Act: -0.0006

Data Index: 956588 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0364. Min Act: -0.0006

Data Index: 27716 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0344. Min Act: -0.0006

Data Index: 880978 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0333. Min Act: -0.0006

Data Index: 847224 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1340372 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0321. Min Act: -0.0006

Data Index: 392781 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0328. Min Act: -0.0006

Data Index: 687594 (C4 (Web Text))

Max Activating Token Index: 42