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

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

Neuron 2412 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2850. Min Range: -4.2850

Max Act: 4.2850. Min Act: -0.0000

Data Index: 342348 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.3290. Min Act: -0.0000

Data Index: 1218232 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.3112. Min Act: -0.0000

Data Index: 8075 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 4.2850. Min Range: -4.2850

Max Act: 2.8571. Min Act: -0.0000

Data Index: 1246249 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.3250. Min Act: -0.0000

Data Index: 825723 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.4303. Min Act: -0.0000

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.2089. Min Act: -0.0000

Data Index: 307348 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.3230. Min Act: -0.0000

Data Index: 793731 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.0355. Min Act: -0.0000

Data Index: 1316716 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.2515. Min Act: -0.0000

Data Index: 2835 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.1183. Min Act: -0.0000

Data Index: 212109 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.0925. Min Act: -0.0000

Data Index: 834292 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.0561. Min Act: -0.0000

Data Index: 449428 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.0389. Min Act: -0.0000

Data Index: 38566 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 4.2850. Min Range: -4.2850

Max Act: 2.8388. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 4.2850. Min Range: -4.2850

Max Act: 3.0783. Min Act: -0.0000

Data Index: 405256 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 4.2850. Min Range: -4.2850

Max Act: 2.9201. Min Act: -0.0000

Data Index: 2210 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 4.2850. Min Range: -4.2850

Max Act: 2.5404. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 4.2850. Min Range: -4.2850

Max Act: 2.9033. Min Act: -0.0000

Data Index: 1240166 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 4.2850. Min Range: -4.2850

Max Act: 2.8901. Min Act: -0.0000

Data Index: 383131 (C4 (Web Text))

Max Activating Token Index: 131