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

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

Neuron 4765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.4325. Min Act: -0.0000

Data Index: 435973 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.4408. Min Act: -0.0000

Data Index: 305626 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.4429. Min Act: -0.0000

Data Index: 694977 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.4398. Min Act: -0.0000

Data Index: 148384 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.2272. Min Act: -0.0000

Data Index: 183196 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.3271. Min Act: -0.0000

Data Index: 1045946 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.4341. Min Act: -0.0000

Data Index: 618139 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.2896. Min Act: -0.0000

Data Index: 20000 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.4429. Min Range: -2.4429

Max Act: 2.3322. Min Act: -0.0000

Data Index: 1205927 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.9298. Min Act: -0.0000

Data Index: 725225 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1174961 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1184083 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.6289. Min Act: -0.0000

Data Index: 709734 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.5239. Min Act: -0.0000

Data Index: 858634 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.4201. Min Act: -0.0000

Data Index: 426851 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.4837. Min Act: -0.0000

Data Index: 758703 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.4022. Min Act: -0.0000

Data Index: 537415 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.3974. Min Act: -0.0000

Data Index: 275985 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.4000. Min Act: -0.0000

Data Index: 767727 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.4429. Min Range: -2.4429

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1048555 (C4 (Web Text))

Max Activating Token Index: 650