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

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

Neuron 3719 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7854. Min Act: -0.0001

Data Index: 490644 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6981. Min Act: -0.0000

Data Index: 92977 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1248755 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1166626 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7294. Min Act: -0.0000

Data Index: 883215 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6976. Min Act: -0.0000

Data Index: 744604 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7126. Min Act: -0.0000

Data Index: 82801 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7101. Min Act: -0.0000

Data Index: 587170 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1308907 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7186. Min Act: -0.0000

Data Index: 68643 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6758. Min Act: -0.0000

Data Index: 768144 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6945. Min Act: -0.0000

Data Index: 997646 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6719. Min Act: -0.0001

Data Index: 417379 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6901. Min Act: -0.0000

Data Index: 818112 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6589. Min Act: -0.0000

Data Index: 835027 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6810. Min Act: -0.0000

Data Index: 390481 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6559. Min Act: -0.0001

Data Index: 967358 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6250. Min Act: -0.0000

Data Index: 143699 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.5713. Min Act: -0.0001

Data Index: 181023 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6021. Min Act: -0.0001

Data Index: 264334 (C4 (Web Text))

Max Activating Token Index: 302