Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1567 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0335. Min Act: -0.0006

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0341. Min Act: -0.0006

Data Index: 339837 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1000646 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0321. Min Act: -0.0006

Data Index: 105840 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1166574 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0316. Min Act: -0.0006

Data Index: 886844 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0313. Min Act: -0.0006

Data Index: 594824 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0309. Min Act: -0.0006

Data Index: 744476 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1439306 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0307. Min Act: -0.0006

Data Index: 698362 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0304. Min Act: -0.0006

Data Index: 441346 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0303. Min Act: -0.0006

Data Index: 914329 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1076776 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1118207 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1022767 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0300. Min Act: -0.0005

Data Index: 313447 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0301. Min Act: -0.0006

Data Index: 556256 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0306. Min Act: -0.0006

Data Index: 204911 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0313. Min Act: -0.0006

Data Index: 1312658 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0312. Min Act: -0.0006

Data Index: 995950 (C4 (Web Text))

Max Activating Token Index: 494