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

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

Neuron 4429 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: 4.6749. Min Range: -4.6749

Max Act: 4.6749. Min Act: -0.0000

Data Index: 245214 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 4.6749. Min Range: -4.6749

Max Act: 4.6249. Min Act: -0.0000

Data Index: 584030 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 4.6749. Min Range: -4.6749

Max Act: 4.5146. Min Act: -0.0000

Data Index: 860173 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 4.6749. Min Range: -4.6749

Max Act: 4.3098. Min Act: -0.0000

Data Index: 612904 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 4.6749. Min Range: -4.6749

Max Act: 4.0149. Min Act: -0.0000

Data Index: 888412 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 4.6749. Min Range: -4.6749

Max Act: 4.1450. Min Act: -0.0000

Data Index: 487365 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 4.6749. Min Range: -4.6749

Max Act: 4.1287. Min Act: -0.0000

Data Index: 804067 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.9645. Min Act: -0.0000

Data Index: 185097 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.7627. Min Act: -0.0000

Data Index: 267307 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.8051. Min Act: -0.0000

Data Index: 1001179 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.7742. Min Act: -0.0000

Data Index: 743548 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.6934. Min Act: -0.0000

Data Index: 891545 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.6254. Min Act: -0.0000

Data Index: 936251 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.6097. Min Act: -0.0000

Data Index: 790343 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.6343. Min Act: -0.0000

Data Index: 1326793 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.7411. Min Act: -0.0000

Data Index: 1055665 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.7220. Min Act: -0.0000

Data Index: 775716 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.3863. Min Act: -0.0000

Data Index: 1178836 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.7137. Min Act: -0.0000

Data Index: 1316272 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 4.6749. Min Range: -4.6749

Max Act: 3.2525. Min Act: -0.0000

Data Index: 710316 (C4 (Web Text))

Max Activating Token Index: 948