Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3681 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1339. Min Range: -3.1339

Max Act: 3.1339. Min Act: -0.0000

Data Index: 1085870 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.6820. Min Act: -0.0000

Data Index: 303134 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.5885. Min Act: -0.0000

Data Index: 1062300 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.9204. Min Act: -0.0000

Data Index: 562959 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.2774. Min Act: -0.0000

Data Index: 611220 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.1582. Min Act: -0.0000

Data Index: 962221 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.0867. Min Act: -0.0000

Data Index: 774822 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.9873. Min Act: -0.0000

Data Index: 994630 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.0993. Min Act: -0.0000

Data Index: 316458 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.2009. Min Act: -0.0000

Data Index: 1217393 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.3080. Min Act: -0.0000

Data Index: 980013 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.1848. Min Act: -0.0000

Data Index: 1060445 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.1638. Min Act: -0.0000

Data Index: 587448 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.1368. Min Act: -0.0000

Data Index: 757138 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.8663. Min Act: -0.0000

Data Index: 899278 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.1339. Min Range: -3.1339

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1057771 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.9483. Min Act: -0.0000

Data Index: 600654 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.9334. Min Act: -0.0000

Data Index: 130731 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.9039. Min Act: -0.0000

Data Index: 692403 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 3.1339. Min Range: -3.1339

Max Act: 1.9019. Min Act: -0.0000

Data Index: 33452 (C4 (Web Text))

Max Activating Token Index: 826