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

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

Neuron 4120 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6482. Min Range: -2.6482

Max Act: 2.6482. Min Act: -0.0001

Data Index: 1025066 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1352434 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.8661. Min Act: -0.0001

Data Index: 763931 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.6353. Min Act: -0.0001

Data Index: 450766 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.5506. Min Act: -0.0000

Data Index: 193200 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.6653. Min Act: -0.0000

Data Index: 717344 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1188913 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.7150. Min Act: -0.0001

Data Index: 519318 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.5716. Min Act: -0.0000

Data Index: 423954 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.5659. Min Act: -0.0000

Data Index: 777051 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.6350. Min Act: -0.0000

Data Index: 707777 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.3166. Min Act: -0.0001

Data Index: 919615 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.3385. Min Act: -0.0000

Data Index: 871037 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.0138. Min Act: -0.0000

Data Index: 214118 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.4800. Min Act: -0.0000

Data Index: 877982 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.3404. Min Act: -0.0000

Data Index: 556846 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1318432 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.2506. Min Act: -0.0000

Data Index: 447586 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.2367. Min Act: -0.0001

Data Index: 1343668 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 2.6482. Min Range: -2.6482

Max Act: 1.3708. Min Act: -0.0000

Data Index: 281560 (C4 (Web Text))

Max Activating Token Index: 977