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

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

Neuron 514 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: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: 0.0001

Data Index: 1014005 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1808. Min Act: -0.0001

Data Index: 808981 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1180599 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1529. Min Act: -0.0001

Data Index: 43717 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1231861 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1492. Min Act: -0.0001

Data Index: 969772 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1423. Min Act: -0.0001

Data Index: 624627 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1428. Min Act: -0.0001

Data Index: 190514 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1364. Min Act: -0.0001

Data Index: 135351 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1405. Min Act: -0.0001

Data Index: 449981 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1356. Min Act: -0.0001

Data Index: 542310 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1399. Min Act: -0.0001

Data Index: 784411 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1010641 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1301. Min Act: -0.0001

Data Index: 181684 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1375. Min Act: -0.0001

Data Index: 58922 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1366. Min Act: -0.0001

Data Index: 152962 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1389. Min Act: -0.0001

Data Index: 652486 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1261939 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1327. Min Act: -0.0001

Data Index: 840025 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1315. Min Act: -0.0001

Data Index: 18165 (C4 (Web Text))

Max Activating Token Index: 131