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

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

Neuron 3005 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.4257. Min Act: -0.0000

Data Index: 842630 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1088385 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3778. Min Act: -0.0000

Data Index: 929247 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1578. Min Act: -0.0000

Data Index: 139407 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.2331. Min Act: -0.0000

Data Index: 93466 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1173094 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1686. Min Act: -0.0000

Data Index: 570844 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1983. Min Act: -0.0000

Data Index: 576919 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1028978 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1247220 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1279343 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1614. Min Act: -0.0000

Data Index: 260251 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1266. Min Act: -0.0000

Data Index: 270912 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0551. Min Act: -0.0000

Data Index: 164571 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1800. Min Act: -0.0000

Data Index: 601647 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0439. Min Act: -0.0000

Data Index: 946978 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1126348 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0038. Min Act: -0.0000

Data Index: 867212 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0126. Min Act: -0.0000

Data Index: 896066 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1092801 (C4 (Web Text))

Max Activating Token Index: 274