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

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

Neuron 2011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.4902. Min Act: -0.0000

Data Index: 211391 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.6455. Min Act: -0.0000

Data Index: 442836 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.4040. Min Act: -0.0000

Data Index: 27670 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.2378. Min Act: -0.0000

Data Index: 1352036 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.3187. Min Act: -0.0000

Data Index: 687184 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.3086. Min Act: -0.0000

Data Index: 1196095 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 4.6455. Min Range: -4.6455

Max Act: 4.2523. Min Act: -0.0000

Data Index: 221240 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.8581. Min Act: -0.0000

Data Index: 1225079 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.9600. Min Act: -0.0000

Data Index: 1001192 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.9260. Min Act: -0.0000

Data Index: 1041674 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.9218. Min Act: -0.0000

Data Index: 177476 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.8940. Min Act: -0.0000

Data Index: 642523 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.8899. Min Act: -0.0000

Data Index: 609315 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.8786. Min Act: -0.0000

Data Index: 341515 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.6616. Min Act: -0.0000

Data Index: 1135225 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.7940. Min Act: -0.0000

Data Index: 637289 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.6176. Min Act: -0.0000

Data Index: 579280 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.9381. Min Act: -0.0000

Data Index: 9187 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.9319. Min Act: -0.0000

Data Index: 263859 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 4.6455. Min Range: -4.6455

Max Act: 3.9272. Min Act: -0.0000

Data Index: 459289 (C4 (Web Text))

Max Activating Token Index: 56