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

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

Neuron 5080 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.3871. Min Act: -0.0000

Data Index: 900205 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 3.3871. Min Range: -3.3871

Max Act: 3.1708. Min Act: -0.0000

Data Index: 979299 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.7364. Min Act: -0.0000

Data Index: 625711 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.7160. Min Act: -0.0000

Data Index: 772983 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.5373. Min Act: -0.0000

Data Index: 1352179 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.6633. Min Act: -0.0000

Data Index: 1293228 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.4873. Min Act: -0.0000

Data Index: 1207082 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.5569. Min Act: -0.0000

Data Index: 753385 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.5249. Min Act: -0.0000

Data Index: 266035 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.3959. Min Act: -0.0000

Data Index: 601205 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.3412. Min Act: -0.0000

Data Index: 1105813 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.4310. Min Act: -0.0000

Data Index: 174488 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.1679. Min Act: -0.0000

Data Index: 270336 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.1483. Min Act: -0.0000

Data Index: 85714 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.1554. Min Act: -0.0000

Data Index: 938221 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.2565. Min Act: -0.0000

Data Index: 625406 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.2307. Min Act: -0.0000

Data Index: 297704 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.1066. Min Act: -0.0000

Data Index: 80151 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.0767. Min Act: -0.0000

Data Index: 254331 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 3.3871. Min Range: -3.3871

Max Act: 2.1837. Min Act: -0.0000

Data Index: 584917 (C4 (Web Text))

Max Activating Token Index: 926