Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2035 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0003

Data Index: 928607 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0511. Min Act: -0.0004

Data Index: 851901 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0509. Min Act: -0.0003

Data Index: 654161 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0481. Min Act: -0.0003

Data Index: 466269 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0484. Min Act: -0.0003

Data Index: 254337 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0467. Min Act: -0.0003

Data Index: 643083 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0465. Min Act: -0.0003

Data Index: 835125 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0475. Min Act: -0.0004

Data Index: 296776 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0453. Min Act: -0.0003

Data Index: 703866 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1250770 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0471. Min Act: -0.0003

Data Index: 348242 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0438. Min Act: -0.0003

Data Index: 305946 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1218538 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0439. Min Act: -0.0003

Data Index: 475823 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0430. Min Act: -0.0003

Data Index: 471596 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0448. Min Act: -0.0003

Data Index: 929297 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0434. Min Act: -0.0003

Data Index: 640789 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0433. Min Act: -0.0003

Data Index: 464744 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0413. Min Act: -0.0003

Data Index: 670865 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0415. Min Act: -0.0003

Data Index: 186345 (C4 (Web Text))

Max Activating Token Index: 691