Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1063. Min Range: -2.1063

Max Act: 2.1063. Min Act: -0.0000

Data Index: 565651 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7981. Min Act: -0.0000

Data Index: 804163 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7553. Min Act: -0.0000

Data Index: 930012 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6991. Min Act: -0.0000

Data Index: 217824 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7661. Min Act: -0.0000

Data Index: 1336774 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7369. Min Act: -0.0000

Data Index: 551939 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6725. Min Act: -0.0000

Data Index: 1028858 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4502. Min Act: -0.0000

Data Index: 17298 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6113. Min Act: -0.0000

Data Index: 713332 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6746. Min Act: -0.0000

Data Index: 134858 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1028693 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6202. Min Act: -0.0000

Data Index: 743144 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6867. Min Act: -0.0000

Data Index: 274605 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1147955 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5059. Min Act: -0.0000

Data Index: 867483 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5356. Min Act: -0.0000

Data Index: 1183145 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1508080 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4066. Min Act: -0.0000

Data Index: 101522 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4984. Min Act: -0.0000

Data Index: 655699 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4099. Min Act: -0.0000

Data Index: 686088 (C4 (Web Text))

Max Activating Token Index: 148