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

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

Neuron 4210 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: 0.9633. Min Range: -0.9633

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1160206 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1356984 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7459. Min Act: -0.0000

Data Index: 261513 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7203. Min Act: -0.0000

Data Index: 817438 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1288022 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7052. Min Act: -0.0000

Data Index: 110197 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6991. Min Act: -0.0000

Data Index: 198937 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6965. Min Act: -0.0000

Data Index: 171546 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6656. Min Act: -0.0000

Data Index: 675987 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1302828 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6772. Min Act: -0.0000

Data Index: 539548 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6476. Min Act: -0.0000

Data Index: 713990 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6511. Min Act: -0.0000

Data Index: 247476 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6186. Min Act: -0.0000

Data Index: 30966 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6290. Min Act: -0.0000

Data Index: 730011 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6120. Min Act: -0.0000

Data Index: 471032 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6245. Min Act: -0.0000

Data Index: 611634 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6182. Min Act: -0.0000

Data Index: 719872 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6402. Min Act: -0.0000

Data Index: 850091 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1222260 (C4 (Web Text))

Max Activating Token Index: 680