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

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

Neuron 2070 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0495. Min Act: -0.0003

Data Index: 996257 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0003

Data Index: 533013 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0415. Min Act: -0.0002

Data Index: 276984 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0428. Min Act: -0.0003

Data Index: 265302 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0433. Min Act: -0.0003

Data Index: 178416 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0416. Min Act: -0.0003

Data Index: 673705 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0398. Min Act: -0.0003

Data Index: 236282 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1173156 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0306. Min Act: -0.0002

Data Index: 275041 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0343. Min Act: -0.0003

Data Index: 24003 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0370. Min Act: -0.0003

Data Index: 214772 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0348. Min Act: -0.0003

Data Index: 8500 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1041664 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0406. Min Act: -0.0003

Data Index: 452349 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0387. Min Act: -0.0003

Data Index: 889254 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0499. Min Act: -0.0003

Data Index: 169858 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1271573 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0369. Min Act: -0.0003

Data Index: 710588 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0420. Min Act: -0.0003

Data Index: 672437 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0378. Min Act: -0.0003

Data Index: 582201 (C4 (Web Text))

Max Activating Token Index: 171