Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2324 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2277. Min Range: -1.2277

Max Act: 1.2277. Min Act: -0.0001

Data Index: 275365 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.2277. Min Range: -1.2277

Max Act: 1.1919. Min Act: -0.0002

Data Index: 1059795 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1295083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1400857 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0913. Min Act: -0.0002

Data Index: 573440 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0541. Min Act: -0.0001

Data Index: 382206 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1533839 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0525. Min Act: -0.0002

Data Index: 655543 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1374343 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1375545 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0243. Min Act: -0.0001

Data Index: 771060 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1366486 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1084338 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1645718 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0209. Min Act: -0.0002

Data Index: 446995 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1041317 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0192. Min Act: -0.0002

Data Index: 364826 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1580569 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1605077 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 1.2277. Min Range: -1.2277

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1548720 (Python Code)

Max Activating Token Index: 522