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

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

Neuron 463 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: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0003

Data Index: 635792 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0512. Min Act: -0.0003

Data Index: 370195 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1048237 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0471. Min Act: -0.0003

Data Index: 343100 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0486. Min Act: -0.0002

Data Index: 614193 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1228439 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1052475 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0444. Min Act: -0.0003

Data Index: 791637 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0466. Min Act: -0.0004

Data Index: 568664 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0442. Min Act: -0.0003

Data Index: 753413 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0463. Min Act: -0.0003

Data Index: 175291 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0476. Min Act: -0.0003

Data Index: 405084 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0432. Min Act: -0.0003

Data Index: 958718 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0428. Min Act: -0.0003

Data Index: 728155 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1137381 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0429. Min Act: -0.0003

Data Index: 309729 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1117940 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0412. Min Act: -0.0004

Data Index: 844139 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1164296 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0436. Min Act: -0.0004

Data Index: 535673 (C4 (Web Text))

Max Activating Token Index: 731