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

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

Neuron 4964 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5141. Min Range: -5.5141

Max Act: 5.5141. Min Act: -0.0000

Data Index: 512700 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 5.5141. Min Range: -5.5141

Max Act: 5.3330. Min Act: -0.0000

Data Index: 943108 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 5.5141. Min Range: -5.5141

Max Act: 5.2842. Min Act: -0.0000

Data Index: 190304 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 5.5141. Min Range: -5.5141

Max Act: 5.0919. Min Act: -0.0000

Data Index: 216842 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 5.5141. Min Range: -5.5141

Max Act: 5.0427. Min Act: -0.0000

Data Index: 1116686 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 5.5141. Min Range: -5.5141

Max Act: 5.1613. Min Act: -0.0000

Data Index: 768982 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.9034. Min Act: -0.0000

Data Index: 611715 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.8196. Min Act: -0.0000

Data Index: 254104 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.9401. Min Act: -0.0000

Data Index: 200319 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.7487. Min Act: -0.0001

Data Index: 912045 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.4716. Min Act: -0.0000

Data Index: 1299639 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.6405. Min Act: -0.0000

Data Index: 771382 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.4588. Min Act: -0.0000

Data Index: 90245 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.3535. Min Act: -0.0000

Data Index: 393704 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.3373. Min Act: -0.0000

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.6788. Min Act: -0.0000

Data Index: 361797 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.6862. Min Act: -0.0000

Data Index: 264708 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.6662. Min Act: -0.0000

Data Index: 194790 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.4705. Min Act: -0.0000

Data Index: 278368 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 5.5141. Min Range: -5.5141

Max Act: 4.3233. Min Act: -0.0000

Data Index: 564803 (C4 (Web Text))

Max Activating Token Index: 530