Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4309 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1341476 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1213414 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.6415. Min Act: -0.0000

Data Index: 210207 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.6830. Min Act: -0.0000

Data Index: 898529 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1220886 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5609. Min Act: -0.0000

Data Index: 607465 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5757. Min Act: -0.0000

Data Index: 667214 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5463. Min Act: -0.0000

Data Index: 990200 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5058. Min Act: -0.0000

Data Index: 824727 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4900. Min Act: -0.0000

Data Index: 938342 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5077. Min Act: -0.0000

Data Index: 196832 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5327. Min Act: -0.0000

Data Index: 752229 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1224265 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5272. Min Act: -0.0000

Data Index: 901670 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5037. Min Act: -0.0000

Data Index: 145382 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1177206 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4209. Min Act: -0.0000

Data Index: 851078 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4401. Min Act: -0.0000

Data Index: 576635 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1283811 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4394. Min Act: -0.0000

Data Index: 244344 (C4 (Web Text))

Max Activating Token Index: 923