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

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

Neuron 1207 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.1608. Min Act: -0.0000

Data Index: 1550873 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.0798. Min Act: -0.0000

Data Index: 676678 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.1247. Min Act: -0.0000

Data Index: 1261451 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.1311. Min Act: -0.0000

Data Index: 887601 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.2331. Min Act: -0.0000

Data Index: 939870 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.0676. Min Act: -0.0000

Data Index: 325750 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.9984. Min Act: -0.0000

Data Index: 870392 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.8930. Min Act: -0.0000

Data Index: 831107 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.8723. Min Act: -0.0000

Data Index: 762703 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.0779. Min Act: -0.0000

Data Index: 543635 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1327274 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.9394. Min Act: -0.0000

Data Index: 1572860 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.0403. Min Act: -0.0000

Data Index: 823489 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.7706. Min Act: -0.0000

Data Index: 1196391 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1441803 (Python Code)

Max Activating Token Index: 846

Text #15

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.9066. Min Act: -0.0000

Data Index: 253673 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.7502. Min Act: -0.0000

Data Index: 1157183 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.8086. Min Act: -0.0000

Data Index: 1184072 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1007562 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.0030. Min Act: -0.0000

Data Index: 1236136 (C4 (Web Text))

Max Activating Token Index: 825