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

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

Neuron 2448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.8516. Min Act: -0.0000

Data Index: 595161 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.8232. Min Act: -0.0000

Data Index: 566026 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7772. Min Act: -0.0000

Data Index: 218519 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.6821. Min Act: -0.0001

Data Index: 133251 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.7432. Min Act: -0.0000

Data Index: 406197 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.6917. Min Act: -0.0000

Data Index: 627734 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1455195 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.6424. Min Act: -0.0001

Data Index: 340504 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.6958. Min Act: -0.0000

Data Index: 268519 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.5655. Min Act: -0.0001

Data Index: 256623 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.4831. Min Act: -0.0001

Data Index: 280200 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.5556. Min Act: -0.0000

Data Index: 820827 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.4413. Min Act: -0.0001

Data Index: 1023307 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.4086. Min Act: -0.0000

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.3580. Min Act: -0.0000

Data Index: 587272 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.4234. Min Act: -0.0000

Data Index: 681775 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.4129. Min Act: -0.0000

Data Index: 517198 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.3032. Min Act: -0.0000

Data Index: 693091 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1386681 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 1.8516. Min Range: -1.8516

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1156868 (C4 (Web Text))

Max Activating Token Index: 575