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

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

Neuron 4434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.5314. Min Act: -0.0000

Data Index: 134053 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4092. Min Act: -0.0000

Data Index: 411433 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1036848 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1019143 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1317384 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3872. Min Act: -0.0000

Data Index: 125572 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1045439 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1039910 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3680. Min Act: -0.0000

Data Index: 814286 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1113537 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3753. Min Act: -0.0000

Data Index: 453173 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3454. Min Act: -0.0000

Data Index: 587287 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3180. Min Act: -0.0000

Data Index: 365112 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1157292 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3223. Min Act: -0.0000

Data Index: 643636 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3576. Min Act: -0.0000

Data Index: 814777 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3362. Min Act: -0.0000

Data Index: 17086 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1085730 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3339. Min Act: -0.0000

Data Index: 134014 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.5314. Min Range: -0.5314

Max Act: 0.3294. Min Act: -0.0000

Data Index: 700565 (C4 (Web Text))

Max Activating Token Index: 905