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

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

Neuron 1518 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: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0002

Data Index: 481710 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1364587 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1403551 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0404. Min Act: -0.0002

Data Index: 720251 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1558326 (Python Code)

Max Activating Token Index: 419

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1649513 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1570699 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1623597 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1554072 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1389475 (Python Code)

Max Activating Token Index: 733

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1622238 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1646248 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1505984 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0392. Min Act: -0.0002

Data Index: 514753 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1523472 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1573053 (Python Code)

Max Activating Token Index: 1022

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1560919 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1427078 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1592186 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1652649 (Python Code)

Max Activating Token Index: 714