Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 625 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0448. Min Act: -0.0004

Data Index: 1196201 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0003

Data Index: 803312 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0423. Min Act: -0.0004

Data Index: 54159 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0415. Min Act: -0.0004

Data Index: 201277 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0405. Min Act: -0.0003

Data Index: 47950 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0403. Min Act: -0.0004

Data Index: 261567 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1031780 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0400. Min Act: -0.0002

Data Index: 965895 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0394. Min Act: -0.0004

Data Index: 505846 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0383. Min Act: -0.0003

Data Index: 72930 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0387. Min Act: -0.0003

Data Index: 934224 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0401. Min Act: -0.0003

Data Index: 109225 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0377. Min Act: -0.0003

Data Index: 844924 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0385. Min Act: -0.0004

Data Index: 769315 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0373. Min Act: -0.0003

Data Index: 662620 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0365. Min Act: -0.0003

Data Index: 707314 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0373. Min Act: -0.0003

Data Index: 141223 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1170962 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0371. Min Act: -0.0003

Data Index: 82266 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0369. Min Act: -0.0003

Data Index: 599168 (C4 (Web Text))

Max Activating Token Index: 813