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

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

Neuron 4214 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.8394. Min Act: 0.0001

Data Index: 1237485 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.5850. Min Act: 0.0000

Data Index: 170367 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.3217. Min Act: 0.0001

Data Index: 408994 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.3056. Min Act: 0.0000

Data Index: 684384 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1043. Min Act: -0.0000

Data Index: 1190718 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1527. Min Act: -0.0000

Data Index: 1017042 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.0537. Min Act: -0.0000

Data Index: 1113090 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1419. Min Act: -0.0000

Data Index: 571406 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1440. Min Act: 0.0000

Data Index: 860919 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1315. Min Act: 0.0001

Data Index: 1085914 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1262. Min Act: 0.0000

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.0580. Min Act: 0.0003

Data Index: 1354466 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 2.8394. Min Range: -2.8394

Max Act: 1.9349. Min Act: -0.0000

Data Index: 703199 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.0172. Min Act: 0.0001

Data Index: 4827 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.0029. Min Act: 0.0000

Data Index: 1331930 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 2.8394. Min Range: -2.8394

Max Act: 2.1107. Min Act: 0.0000

Data Index: 892829 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.8394. Min Range: -2.8394

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1196756 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 2.8394. Min Range: -2.8394

Max Act: 1.9924. Min Act: -0.0000

Data Index: 485928 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 2.8394. Min Range: -2.8394

Max Act: 1.9599. Min Act: -0.0000

Data Index: 753725 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 2.8394. Min Range: -2.8394

Max Act: 1.9582. Min Act: -0.0000

Data Index: 1210428 (C4 (Web Text))

Max Activating Token Index: 290