Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5261 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1303077 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3139. Min Act: -0.0001

Data Index: 696403 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2823. Min Act: -0.0001

Data Index: 647371 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2827. Min Act: -0.0000

Data Index: 843465 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2639. Min Act: -0.0000

Data Index: 879559 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2811. Min Act: -0.0000

Data Index: 559877 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2560. Min Act: -0.0001

Data Index: 279826 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2476. Min Act: -0.0001

Data Index: 607414 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2338. Min Act: -0.0001

Data Index: 952501 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2756. Min Act: -0.0000

Data Index: 823195 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2811. Min Act: -0.0000

Data Index: 66501 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2476. Min Act: -0.0000

Data Index: 223275 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2732. Min Act: -0.0001

Data Index: 172291 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1103911 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2500. Min Act: -0.0001

Data Index: 599861 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2528. Min Act: -0.0001

Data Index: 987252 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2621. Min Act: -0.0001

Data Index: 650139 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1162169 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1010858 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2361. Min Act: -0.0001

Data Index: 61118 (C4 (Web Text))

Max Activating Token Index: 568