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

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

Neuron 95 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: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0002

Data Index: 1117541 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1585. Min Act: -0.0002

Data Index: 1339318 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1566. Min Act: -0.0002

Data Index: 423666 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1557. Min Act: -0.0002

Data Index: 878442 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1483. Min Act: -0.0002

Data Index: 524330 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1502. Min Act: -0.0002

Data Index: 223655 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1469. Min Act: -0.0002

Data Index: 460091 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1467. Min Act: -0.0002

Data Index: 718085 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1496. Min Act: -0.0002

Data Index: 134834 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1441. Min Act: -0.0002

Data Index: 933354 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1375673 (Python Code)

Max Activating Token Index: 424

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1442. Min Act: -0.0002

Data Index: 549550 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1441. Min Act: -0.0002

Data Index: 985665 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1465. Min Act: -0.0002

Data Index: 228154 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1417. Min Act: -0.0002

Data Index: 842594 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1403. Min Act: -0.0002

Data Index: 1030661 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1383. Min Act: -0.0002

Data Index: 631757 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1356. Min Act: -0.0002

Data Index: 917792 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1356. Min Act: -0.0002

Data Index: 315015 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1404. Min Act: -0.0002

Data Index: 239448 (C4 (Web Text))

Max Activating Token Index: 276