Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.2984. Min Act: -0.0000

Data Index: 1086042 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9204. Min Act: -0.0000

Data Index: 1301887 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9821. Min Act: -0.0001

Data Index: 818823 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.1675. Min Act: -0.0000

Data Index: 1279309 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.0449. Min Act: -0.0001

Data Index: 691488 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.1128. Min Act: -0.0000

Data Index: 702876 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.0044. Min Act: -0.0000

Data Index: 404636 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9879. Min Act: -0.0000

Data Index: 1197431 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.0330. Min Act: -0.0000

Data Index: 580277 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9975. Min Act: -0.0000

Data Index: 407266 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9528. Min Act: -0.0000

Data Index: 209017 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.0447. Min Act: -0.0000

Data Index: 1029654 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9108. Min Act: -0.0000

Data Index: 140887 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.8655. Min Act: -0.0000

Data Index: 992051 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 2.2984. Min Range: -2.2984

Max Act: 2.0183. Min Act: -0.0000

Data Index: 210733 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.8312. Min Act: -0.0000

Data Index: 603605 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.8144. Min Act: -0.0000

Data Index: 1020445 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.7369. Min Act: -0.0000

Data Index: 866515 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.9341. Min Act: -0.0000

Data Index: 699700 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 2.2984. Min Range: -2.2984

Max Act: 1.7166. Min Act: -0.0000

Data Index: 928970 (C4 (Web Text))

Max Activating Token Index: 212