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

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

Neuron 1107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1350540 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0495. Min Act: -0.0006

Data Index: 91635 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0485. Min Act: -0.0006

Data Index: 55134 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0473. Min Act: -0.0006

Data Index: 1112399 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0467. Min Act: -0.0006

Data Index: 1347309 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0438. Min Act: -0.0006

Data Index: 727623 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0437. Min Act: -0.0006

Data Index: 576060 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0443. Min Act: -0.0006

Data Index: 352866 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0443. Min Act: -0.0006

Data Index: 1267281 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0431. Min Act: -0.0006

Data Index: 450365 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0449. Min Act: -0.0006

Data Index: 63957 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0445. Min Act: -0.0006

Data Index: 439791 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0435. Min Act: -0.0006

Data Index: 496295 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0431. Min Act: -0.0006

Data Index: 207151 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0421. Min Act: -0.0006

Data Index: 560839 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0421. Min Act: -0.0006

Data Index: 682197 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0436. Min Act: -0.0006

Data Index: 1121587 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0425. Min Act: -0.0006

Data Index: 486287 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0421. Min Act: -0.0006

Data Index: 576546 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0417. Min Act: -0.0006

Data Index: 62273 (C4 (Web Text))

Max Activating Token Index: 95