Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1271591 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0003

Data Index: 659194 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1338825 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0502. Min Act: -0.0003

Data Index: 643648 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1040920 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0503. Min Act: -0.0003

Data Index: 593523 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0459. Min Act: -0.0003

Data Index: 483063 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0464. Min Act: -0.0003

Data Index: 257456 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0461. Min Act: -0.0003

Data Index: 38420 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0436. Min Act: -0.0003

Data Index: 141415 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0464. Min Act: -0.0003

Data Index: 194321 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0462. Min Act: -0.0003

Data Index: 659848 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0457. Min Act: -0.0003

Data Index: 644861 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0423. Min Act: -0.0003

Data Index: 88504 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0446. Min Act: -0.0003

Data Index: 653782 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0420. Min Act: -0.0004

Data Index: 893635 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0436. Min Act: -0.0003

Data Index: 161279 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0455. Min Act: -0.0003

Data Index: 67769 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1059547 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0452. Min Act: -0.0003

Data Index: 90541 (C4 (Web Text))

Max Activating Token Index: 93