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

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

Neuron 825 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5151. Min Range: -2.5151

Max Act: 2.5151. Min Act: -0.0000

Data Index: 1164047 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 2.5151. Min Range: -2.5151

Max Act: 2.1403. Min Act: -0.0000

Data Index: 448956 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 2.5151. Min Range: -2.5151

Max Act: 2.0162. Min Act: -0.0000

Data Index: 1194104 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 2.5151. Min Range: -2.5151

Max Act: 2.0927. Min Act: -0.0000

Data Index: 871171 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.8260. Min Act: -0.0000

Data Index: 798500 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1164215 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.7704. Min Act: -0.0000

Data Index: 726871 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.7555. Min Act: -0.0000

Data Index: 706407 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.6364. Min Act: -0.0000

Data Index: 650958 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.7228. Min Act: -0.0000

Data Index: 1208827 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.7128. Min Act: -0.0000

Data Index: 2790 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.5869. Min Act: -0.0000

Data Index: 425242 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.4176. Min Act: 0.0001

Data Index: 31170 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.6588. Min Act: -0.0000

Data Index: 296402 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.8627. Min Act: -0.0000

Data Index: 915324 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.7390. Min Act: -0.0000

Data Index: 739604 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1086226 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.7395. Min Act: -0.0000

Data Index: 107732 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.5503. Min Act: -0.0000

Data Index: 714128 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 2.5151. Min Range: -2.5151

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1270961 (C4 (Web Text))

Max Activating Token Index: 305