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

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

Neuron 5042 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1308. Min Act: -0.0002

Data Index: 713733 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1297. Min Act: -0.0002

Data Index: 477306 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1223. Min Act: -0.0002

Data Index: 607588 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1179. Min Act: -0.0002

Data Index: 566481 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1188. Min Act: -0.0002

Data Index: 789963 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1060532 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1145. Min Act: -0.0002

Data Index: 545159 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1132. Min Act: -0.0002

Data Index: 300912 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1055. Min Act: -0.0002

Data Index: 969768 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0998. Min Act: -0.0002

Data Index: 322331 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1276524 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0958. Min Act: -0.0002

Data Index: 670932 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1150340 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1282722 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0900. Min Act: -0.0002

Data Index: 880207 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0908. Min Act: -0.0002

Data Index: 18801 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0863. Min Act: -0.0002

Data Index: 120406 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1039768 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0797. Min Act: -0.0002

Data Index: 271871 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0785. Min Act: -0.0002

Data Index: 121173 (C4 (Web Text))

Max Activating Token Index: 352