Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1652 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0002

Data Index: 456103 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1239100 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0659. Min Act: -0.0001

Data Index: 527557 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0683. Min Act: -0.0001

Data Index: 242614 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0569. Min Act: -0.0002

Data Index: 711210 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0612. Min Act: -0.0002

Data Index: 725894 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1104607 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0618. Min Act: -0.0001

Data Index: 34079 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1297561 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0595. Min Act: -0.0001

Data Index: 799922 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1031360 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0590. Min Act: -0.0002

Data Index: 885426 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1077230 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0592. Min Act: -0.0001

Data Index: 464978 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1472986 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1296956 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0555. Min Act: -0.0001

Data Index: 204286 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1573848 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0576. Min Act: -0.0001

Data Index: 496826 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1373712 (Python Code)

Max Activating Token Index: 27