Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 660 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.5407. Min Act: -0.0000

Data Index: 529422 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.4335. Min Act: -0.0000

Data Index: 492855 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.3675. Min Act: -0.0000

Data Index: 769762 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.0366. Min Act: -0.0000

Data Index: 442246 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.0870. Min Act: -0.0000

Data Index: 1134584 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.1025. Min Act: -0.0000

Data Index: 948103 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.2522. Min Act: -0.0000

Data Index: 120713 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.0424. Min Act: -0.0000

Data Index: 199120 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 4.5407. Min Range: -4.5407

Max Act: 4.0131. Min Act: -0.0000

Data Index: 943311 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.9494. Min Act: -0.0000

Data Index: 84043 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.9374. Min Act: -0.0000

Data Index: 346207 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.9358. Min Act: -0.0000

Data Index: 656396 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.9250. Min Act: -0.0000

Data Index: 979534 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.9032. Min Act: -0.0000

Data Index: 610992 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.8750. Min Act: -0.0000

Data Index: 1184843 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.8715. Min Act: -0.0000

Data Index: 557764 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.8444. Min Act: -0.0000

Data Index: 1017726 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.8149. Min Act: -0.0000

Data Index: 167042 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.8160. Min Act: -0.0000

Data Index: 1356858 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 4.5407. Min Range: -4.5407

Max Act: 3.8081. Min Act: -0.0000

Data Index: 585869 (C4 (Web Text))

Max Activating Token Index: 370