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

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

Neuron 3831 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.4000. Min Act: -0.0001

Data Index: 254511 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2387. Min Act: -0.0001

Data Index: 62723 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.4044. Min Act: -0.0002

Data Index: 205704 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2567. Min Act: -0.0002

Data Index: 1248761 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2643. Min Act: -0.0001

Data Index: 784879 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2267. Min Act: -0.0002

Data Index: 402696 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2212. Min Act: -0.0001

Data Index: 566865 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1813. Min Act: -0.0001

Data Index: 92703 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1374. Min Act: -0.0002

Data Index: 873484 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2478. Min Act: -0.0002

Data Index: 1334587 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0523. Min Act: -0.0002

Data Index: 711575 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2191. Min Act: -0.0001

Data Index: 1155367 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.2135. Min Act: -0.0002

Data Index: 1215228 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1503. Min Act: -0.0002

Data Index: 1031287 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1071. Min Act: -0.0002

Data Index: 1230541 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0881. Min Act: -0.0001

Data Index: 1097432 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.1024. Min Act: -0.0002

Data Index: 441925 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.4044. Min Range: -1.4044

Max Act: 1.0397. Min Act: -0.0002

Data Index: 1316124 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.4044. Min Range: -1.4044

Max Act: 0.9665. Min Act: -0.0002

Data Index: 996917 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.4044. Min Range: -1.4044

Max Act: 0.9960. Min Act: -0.0001

Data Index: 35430 (C4 (Web Text))

Max Activating Token Index: 552