Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5074 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1508. Min Act: -0.0002

Data Index: 870660 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1500. Min Act: -0.0003

Data Index: 193737 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1530. Min Act: -0.0002

Data Index: 955235 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1298066 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1202289 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1482. Min Act: -0.0002

Data Index: 257994 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1481. Min Act: -0.0002

Data Index: 985622 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1462. Min Act: -0.0002

Data Index: 606089 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1447. Min Act: -0.0002

Data Index: 1290200 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1499. Min Act: -0.0002

Data Index: 324202 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1431. Min Act: -0.0002

Data Index: 507742 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1469. Min Act: -0.0002

Data Index: 596234 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1467. Min Act: -0.0003

Data Index: 492967 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1440. Min Act: -0.0002

Data Index: 70468 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1452. Min Act: -0.0002

Data Index: 154059 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1424. Min Act: -0.0002

Data Index: 1020967 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1426. Min Act: -0.0002

Data Index: 1022922 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1351067 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1415. Min Act: -0.0002

Data Index: 141267 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1073138 (C4 (Web Text))

Max Activating Token Index: 34