Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1994 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0598. Min Act: -0.0003

Data Index: 344227 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0542. Min Act: -0.0003

Data Index: 357181 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0551. Min Act: -0.0003

Data Index: 169592 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0509. Min Act: -0.0003

Data Index: 949610 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1308617 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0500. Min Act: -0.0003

Data Index: 92920 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0504. Min Act: -0.0003

Data Index: 371120 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0501. Min Act: -0.0003

Data Index: 843173 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0525. Min Act: -0.0003

Data Index: 954043 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1260513 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1776 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1182880 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0506. Min Act: -0.0003

Data Index: 36481 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0461. Min Act: -0.0003

Data Index: 619251 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1317877 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0470. Min Act: -0.0003

Data Index: 962336 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0497. Min Act: -0.0003

Data Index: 442075 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1111126 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0476. Min Act: -0.0003

Data Index: 689310 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.0598. Min Range: -0.0598

Max Act: 0.0481. Min Act: -0.0003

Data Index: 649631 (C4 (Web Text))

Max Activating Token Index: 211