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

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

Neuron 1964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0596. Min Act: -0.0002

Data Index: 476869 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0583. Min Act: -0.0002

Data Index: 427468 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0447. Min Act: -0.0002

Data Index: 99796 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0522. Min Act: -0.0002

Data Index: 864918 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 448007 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1190168 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0440. Min Act: -0.0002

Data Index: 507048 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1224976 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0475. Min Act: -0.0002

Data Index: 99329 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0518. Min Act: -0.0002

Data Index: 178540 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1187730 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0467. Min Act: -0.0002

Data Index: 310940 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0500. Min Act: -0.0002

Data Index: 300836 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1281523 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1086977 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1140618 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1645031 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0390. Min Act: -0.0002

Data Index: 498823 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1355648 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1262918 (C4 (Web Text))

Max Activating Token Index: 705