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

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

Neuron 4871 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: 1.4877. Min Range: -1.4877

Max Act: 1.4877. Min Act: -0.0000

Data Index: 485218 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.3294. Min Act: -0.0000

Data Index: 406191 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1183756 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1224954 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1310. Min Act: -0.0000

Data Index: 256091 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1468. Min Act: -0.0000

Data Index: 815352 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1126. Min Act: -0.0001

Data Index: 653990 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1271389 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1213700 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1170568 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0630. Min Act: -0.0000

Data Index: 464326 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0497. Min Act: -0.0001

Data Index: 1303928 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.4877. Min Range: -1.4877

Max Act: 0.9253. Min Act: -0.0000

Data Index: 449574 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0453. Min Act: -0.0001

Data Index: 332099 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.4877. Min Range: -1.4877

Max Act: 1.0117. Min Act: -0.0001

Data Index: 115663 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.4877. Min Range: -1.4877

Max Act: 0.9426. Min Act: -0.0000

Data Index: 71455 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.4877. Min Range: -1.4877

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1148110 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.4877. Min Range: -1.4877

Max Act: 0.9810. Min Act: -0.0000

Data Index: 92281 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 1.4877. Min Range: -1.4877

Max Act: 0.9693. Min Act: -0.0001

Data Index: 944077 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.4877. Min Range: -1.4877

Max Act: 0.9879. Min Act: -0.0000

Data Index: 209368 (C4 (Web Text))

Max Activating Token Index: 717