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

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

Neuron 1645 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.8047. Min Act: -0.0000

Data Index: 167516 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7910. Min Act: -0.0000

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6423. Min Act: -0.0001

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7633. Min Act: -0.0001

Data Index: 1113322 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6465. Min Act: -0.0000

Data Index: 877145 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1240419 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6013. Min Act: -0.0001

Data Index: 1295514 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1094338 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.7223. Min Act: -0.0000

Data Index: 49741 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5871. Min Act: -0.0000

Data Index: 288812 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5821. Min Act: -0.0000

Data Index: 578654 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5580. Min Act: -0.0000

Data Index: 437406 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.6400. Min Act: -0.0000

Data Index: 472193 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5010. Min Act: -0.0000

Data Index: 74560 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1293205 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5756. Min Act: -0.0001

Data Index: 1039953 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5182. Min Act: -0.0000

Data Index: 947286 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.4711. Min Act: -0.0001

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.8047. Min Range: -0.8047

Max Act: 0.5077. Min Act: -0.0001

Data Index: 668712 (C4 (Web Text))

Max Activating Token Index: 515