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

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

Neuron 3081 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1009032 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0345. Min Act: -0.0002

Data Index: 183180 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0371. Min Act: -0.0002

Data Index: 649091 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0328. Min Act: -0.0002

Data Index: 960040 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0344. Min Act: -0.0002

Data Index: 897872 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1511440 (Python Code)

Max Activating Token Index: 341

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0276. Min Act: -0.0002

Data Index: 554808 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0297. Min Act: -0.0002

Data Index: 866063 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1136497 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0276. Min Act: -0.0002

Data Index: 436749 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0255. Min Act: -0.0002

Data Index: 430965 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0264. Min Act: -0.0002

Data Index: 826949 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0252. Min Act: -0.0002

Data Index: 79998 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0260. Min Act: -0.0002

Data Index: 973192 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0225. Min Act: -0.0002

Data Index: 173674 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0261. Min Act: -0.0002

Data Index: 401509 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1326691 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0256. Min Act: -0.0002

Data Index: 621420 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0232. Min Act: -0.0002

Data Index: 55102 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0224. Min Act: -0.0002

Data Index: 759171 (C4 (Web Text))

Max Activating Token Index: 283