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

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

Neuron 1226 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: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0003

Data Index: 208941 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0546. Min Act: -0.0002

Data Index: 291643 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1118622 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0509. Min Act: -0.0003

Data Index: 246836 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1264756 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0511. Min Act: -0.0003

Data Index: 141402 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0491. Min Act: -0.0003

Data Index: 499000 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0496. Min Act: -0.0003

Data Index: 290688 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1129951 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1008676 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0476. Min Act: -0.0002

Data Index: 603752 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0499. Min Act: -0.0004

Data Index: 1356020 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0475. Min Act: -0.0004

Data Index: 304703 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0488. Min Act: -0.0003

Data Index: 421517 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0478. Min Act: -0.0003

Data Index: 939 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0480. Min Act: -0.0003

Data Index: 811020 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0466. Min Act: -0.0003

Data Index: 256726 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0479. Min Act: -0.0002

Data Index: 27781 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1001749 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0469. Min Act: -0.0003

Data Index: 637698 (C4 (Web Text))

Max Activating Token Index: 652