Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 57 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.8359. Min Act: -0.0003

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7980. Min Act: -0.0003

Data Index: 1248321 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.8139. Min Act: -0.0003

Data Index: 268808 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7467. Min Act: -0.0003

Data Index: 1009538 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7011. Min Act: -0.0003

Data Index: 903321 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7268. Min Act: -0.0003

Data Index: 1058497 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6236. Min Act: -0.0003

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.7346. Min Act: -0.0003

Data Index: 272506 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6474. Min Act: -0.0003

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6566. Min Act: -0.0003

Data Index: 1335357 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6050. Min Act: -0.0003

Data Index: 896671 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6819. Min Act: -0.0003

Data Index: 57484 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6784. Min Act: -0.0003

Data Index: 650871 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6452. Min Act: -0.0003

Data Index: 533794 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6242. Min Act: -0.0003

Data Index: 140442 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6717. Min Act: -0.0003

Data Index: 558354 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6407. Min Act: -0.0003

Data Index: 231760 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6004. Min Act: -0.0003

Data Index: 1103973 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6465. Min Act: -0.0003

Data Index: 110128 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.8359. Min Range: -0.8359

Max Act: 0.6244. Min Act: -0.0003

Data Index: 1344755 (C4 (Web Text))

Max Activating Token Index: 575