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

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

Neuron 1367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1958. Min Act: -0.0000

Data Index: 354433 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.2015. Min Act: -0.0000

Data Index: 860087 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1856. Min Act: -0.0000

Data Index: 84347 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1917. Min Act: -0.0000

Data Index: 985131 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1920. Min Act: -0.0000

Data Index: 24556 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1719. Min Act: -0.0000

Data Index: 5922 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1739. Min Act: -0.0001

Data Index: 78871 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1694. Min Act: -0.0001

Data Index: 78764 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1026020 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1312081 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1208531 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1564. Min Act: -0.0000

Data Index: 981236 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1072287 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1422. Min Act: -0.0000

Data Index: 248890 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1315383 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1282646 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1269. Min Act: -0.0000

Data Index: 943962 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1317. Min Act: -0.0000

Data Index: 330741 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1421. Min Act: -0.0000

Data Index: 368649 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1208111 (C4 (Web Text))

Max Activating Token Index: 272