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

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

Neuron 3806 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.8279. Min Act: -0.0000

Data Index: 849750 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6938. Min Act: -0.0001

Data Index: 451303 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.6585. Min Act: -0.0001

Data Index: 637865 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5562. Min Act: -0.0001

Data Index: 586937 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5479. Min Act: -0.0001

Data Index: 1211223 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5312. Min Act: -0.0001

Data Index: 989677 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5134. Min Act: -0.0001

Data Index: 365179 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5317. Min Act: -0.0001

Data Index: 167746 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5446. Min Act: -0.0001

Data Index: 568478 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4881. Min Act: -0.0001

Data Index: 13117 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5219. Min Act: -0.0001

Data Index: 579693 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4978. Min Act: -0.0001

Data Index: 1248397 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1097655 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4933. Min Act: -0.0001

Data Index: 758093 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5222. Min Act: -0.0001

Data Index: 403004 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4738. Min Act: -0.0001

Data Index: 819335 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4870. Min Act: -0.0000

Data Index: 908079 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.5066. Min Act: -0.0001

Data Index: 974391 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4864. Min Act: -0.0001

Data Index: 41681 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.8279. Min Range: -0.8279

Max Act: 0.4886. Min Act: -0.0001

Data Index: 287060 (C4 (Web Text))

Max Activating Token Index: 444