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

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

Neuron 694 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.6319. Min Act: -0.0001

Data Index: 1527084 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4941. Min Act: -0.0001

Data Index: 91777 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5131. Min Act: -0.0001

Data Index: 1396601 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.5370. Min Act: -0.0001

Data Index: 378755 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4616. Min Act: -0.0001

Data Index: 1236747 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4841. Min Act: -0.0001

Data Index: 973044 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4894. Min Act: -0.0001

Data Index: 611378 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4755. Min Act: -0.0001

Data Index: 726240 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4920. Min Act: -0.0001

Data Index: 344488 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1098087 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4778. Min Act: -0.0001

Data Index: 259101 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4405. Min Act: -0.0001

Data Index: 238714 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1073553 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4441. Min Act: -0.0001

Data Index: 343808 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4424. Min Act: -0.0001

Data Index: 758266 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4511. Min Act: -0.0001

Data Index: 101374 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4176. Min Act: -0.0001

Data Index: 643980 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1233559 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4289. Min Act: -0.0001

Data Index: 710635 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.6319. Min Range: -0.6319

Max Act: 0.4020. Min Act: -0.0001

Data Index: 999095 (C4 (Web Text))

Max Activating Token Index: 40