Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 289 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1210694 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1268812 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6618. Min Act: -0.0001

Data Index: 163716 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6448. Min Act: -0.0001

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6269. Min Act: -0.0001

Data Index: 744238 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6352. Min Act: -0.0001

Data Index: 49992 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5893. Min Act: -0.0000

Data Index: 920450 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6006. Min Act: -0.0000

Data Index: 982432 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1159231 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6394. Min Act: -0.0000

Data Index: 208840 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5766. Min Act: -0.0000

Data Index: 68167 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5845. Min Act: -0.0001

Data Index: 527793 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5785. Min Act: -0.0001

Data Index: 157813 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5861. Min Act: -0.0001

Data Index: 64164 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5814. Min Act: -0.0001

Data Index: 1053451 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5645. Min Act: -0.0001

Data Index: 929767 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5533. Min Act: -0.0001

Data Index: 104080 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1290394 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5210. Min Act: -0.0001

Data Index: 926739 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5303. Min Act: -0.0001

Data Index: 424749 (C4 (Web Text))

Max Activating Token Index: 50