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

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

Neuron 2546 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: 2.0040. Min Range: -2.0040

Max Act: 2.0040. Min Act: -0.0000

Data Index: 857229 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.5470. Min Act: -0.0000

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.4513. Min Act: -0.0000

Data Index: 51250 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.1453. Min Act: -0.0000

Data Index: 287014 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.2751. Min Act: -0.0000

Data Index: 330725 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.2347. Min Act: -0.0000

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.2772. Min Act: -0.0000

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.2715. Min Act: -0.0000

Data Index: 405257 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.1898. Min Act: -0.0000

Data Index: 558446 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.0571. Min Act: -0.0000

Data Index: 911142 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.2152. Min Act: -0.0000

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.0957. Min Act: -0.0000

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.1374. Min Act: -0.0000

Data Index: 255414 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1353772 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.0475. Min Act: -0.0000

Data Index: 548341 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.0317. Min Act: -0.0000

Data Index: 568157 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 2.0040. Min Range: -2.0040

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1322655 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.1051. Min Act: -0.0000

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 2.0040. Min Range: -2.0040

Max Act: 1.0182. Min Act: 0.0000

Data Index: 1465879 (Python Code)

Max Activating Token Index: 898