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

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

Neuron 368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2174. Min Range: -1.2174

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1015376 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.2174. Min Range: -1.2174

Max Act: 1.0758. Min Act: -0.0000

Data Index: 925948 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1266707 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.2174. Min Range: -1.2174

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1002822 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.2174. Min Range: -1.2174

Max Act: 1.0143. Min Act: -0.0000

Data Index: 185020 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9568. Min Act: -0.0000

Data Index: 477100 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9205. Min Act: -0.0000

Data Index: 578632 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9407. Min Act: -0.0000

Data Index: 181569 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.9239. Min Act: -0.0000

Data Index: 760228 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8610. Min Act: -0.0000

Data Index: 535543 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8622. Min Act: -0.0000

Data Index: 525214 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1359036 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7562. Min Act: -0.0000

Data Index: 55694 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8311. Min Act: -0.0000

Data Index: 835040 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1354588 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8138. Min Act: -0.0000

Data Index: 984117 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7872. Min Act: -0.0000

Data Index: 634604 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8272. Min Act: -0.0000

Data Index: 816300 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1065376 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.2174. Min Range: -1.2174

Max Act: 0.8139. Min Act: -0.0000

Data Index: 411681 (C4 (Web Text))

Max Activating Token Index: 108