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

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

Neuron 2255 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.3819. Min Act: -0.0001

Data Index: 1169843 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.1236. Min Act: -0.0001

Data Index: 44898 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.1253. Min Act: -0.0001

Data Index: 907223 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.0187. Min Act: -0.0001

Data Index: 658841 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9344. Min Act: -0.0001

Data Index: 1298121 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.0061. Min Act: -0.0001

Data Index: 913759 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9446. Min Act: -0.0001

Data Index: 1104698 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.0521. Min Act: -0.0001

Data Index: 657542 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9647. Min Act: -0.0001

Data Index: 976404 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9660. Min Act: -0.0001

Data Index: 987981 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.3819. Min Range: -1.3819

Max Act: 1.0903. Min Act: -0.0001

Data Index: 74991 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9570. Min Act: -0.0001

Data Index: 1353473 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9577. Min Act: -0.0001

Data Index: 1293109 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.8880. Min Act: -0.0001

Data Index: 1357470 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1396808 (Python Code)

Max Activating Token Index: 341

Text #15

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9224. Min Act: -0.0001

Data Index: 778911 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9777. Min Act: -0.0001

Data Index: 865307 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.9314. Min Act: -0.0001

Data Index: 759905 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.8362. Min Act: -0.0001

Data Index: 1134374 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.3819. Min Range: -1.3819

Max Act: 0.8198. Min Act: -0.0001

Data Index: 88589 (C4 (Web Text))

Max Activating Token Index: 981