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

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

Neuron 211 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: 1.1412. Min Range: -1.1412

Max Act: 1.1412. Min Act: -0.0001

Data Index: 181269 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0301. Min Act: -0.0001

Data Index: 703214 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0442. Min Act: -0.0001

Data Index: 1030329 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0691. Min Act: -0.0001

Data Index: 865442 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0255. Min Act: -0.0001

Data Index: 999780 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0812. Min Act: -0.0001

Data Index: 184565 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0546. Min Act: -0.0001

Data Index: 538138 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9567. Min Act: -0.0001

Data Index: 1025427 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9945. Min Act: -0.0001

Data Index: 379306 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9454. Min Act: -0.0001

Data Index: 130873 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9337. Min Act: -0.0001

Data Index: 750009 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.1412. Min Range: -1.1412

Max Act: 1.0381. Min Act: -0.0001

Data Index: 1353450 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9294. Min Act: -0.0001

Data Index: 1156106 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9522. Min Act: -0.0001

Data Index: 1083215 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9509. Min Act: -0.0001

Data Index: 1218019 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1251570 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.8849. Min Act: -0.0001

Data Index: 51046 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9113. Min Act: -0.0001

Data Index: 658963 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1109474 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.1412. Min Range: -1.1412

Max Act: 0.9108. Min Act: -0.0001

Data Index: 1061391 (C4 (Web Text))

Max Activating Token Index: 675