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

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

Neuron 3753 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: 0.3015. Min Range: -0.3015

Max Act: 0.2942. Min Act: -0.0001

Data Index: 540890 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.3015. Min Act: -0.0000

Data Index: 71063 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2701. Min Act: -0.0001

Data Index: 1181773 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2500. Min Act: -0.0000

Data Index: 658033 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2258. Min Act: -0.0000

Data Index: 957201 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2497. Min Act: -0.0000

Data Index: 330976 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1166502 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2236. Min Act: -0.0000

Data Index: 707063 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1334346 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1891. Min Act: -0.0001

Data Index: 886414 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1831. Min Act: -0.0001

Data Index: 213959 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1136116 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1217702 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1678. Min Act: -0.0001

Data Index: 1054814 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1095523 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1189629 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1685. Min Act: -0.0001

Data Index: 481 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1744. Min Act: -0.0001

Data Index: 910098 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1603. Min Act: -0.0001

Data Index: 305382 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.3015. Min Range: -0.3015

Max Act: 0.1651. Min Act: -0.0000

Data Index: 103140 (C4 (Web Text))

Max Activating Token Index: 804