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

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

Neuron 3066 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1689. Min Act: -0.0001

Data Index: 205531 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1168166 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1725. Min Act: -0.0001

Data Index: 776376 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1559. Min Act: -0.0001

Data Index: 4807 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1555. Min Act: -0.0001

Data Index: 866168 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1555. Min Act: -0.0001

Data Index: 679417 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1426. Min Act: -0.0001

Data Index: 554426 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1432. Min Act: -0.0001

Data Index: 817590 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1174922 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1460. Min Act: -0.0001

Data Index: 483015 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1418. Min Act: -0.0001

Data Index: 529064 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1417. Min Act: -0.0001

Data Index: 704266 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1401. Min Act: -0.0001

Data Index: 51233 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1472. Min Act: -0.0001

Data Index: 430299 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1245386 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1438. Min Act: -0.0001

Data Index: 742449 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1503. Min Act: -0.0001

Data Index: 810466 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1504. Min Act: -0.0001

Data Index: 12369 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1404. Min Act: -0.0001

Data Index: 146004 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1418. Min Act: -0.0001

Data Index: 365017 (C4 (Web Text))

Max Activating Token Index: 202