Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2894 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1168844 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1057881 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1093474 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1652867 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0434. Min Act: -0.0000

Data Index: 21142 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1588984 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1572300 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1653568 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1542441 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1037512 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0416. Min Act: -0.0000

Data Index: 770911 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1376732 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0389. Min Act: -0.0000

Data Index: 499897 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1462659 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1532114 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0414. Min Act: -0.0000

Data Index: 606150 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1579104 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0357. Min Act: -0.0000

Data Index: 335858 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1481376 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1216726 (C4 (Web Text))

Max Activating Token Index: 579