Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 938 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0483. Min Range: -4.0483

Max Act: 4.0483. Min Act: -0.0000

Data Index: 1499688 (Python Code)

Max Activating Token Index: 619

Text #1

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.6439. Min Act: -0.0000

Data Index: 1444394 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.3800. Min Act: -0.0001

Data Index: 1655457 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.3540. Min Act: -0.0000

Data Index: 1563706 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.3459. Min Act: -0.0000

Data Index: 1614019 (Python Code)

Max Activating Token Index: 625

Text #5

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.4239. Min Act: -0.0000

Data Index: 1409117 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.0639. Min Act: -0.0000

Data Index: 1628643 (Python Code)

Max Activating Token Index: 837

Text #7

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.8458. Min Act: -0.0000

Data Index: 1443280 (Python Code)

Max Activating Token Index: 196

Text #8

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.1157. Min Act: -0.0000

Data Index: 1600631 (Python Code)

Max Activating Token Index: 602

Text #9

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.2407. Min Act: -0.0000

Data Index: 1514803 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.9142. Min Act: -0.0000

Data Index: 1529729 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.1949. Min Act: -0.0000

Data Index: 1383715 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.8698. Min Act: -0.0000

Data Index: 1560519 (Python Code)

Max Activating Token Index: 504

Text #13

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.7058. Min Act: -0.0000

Data Index: 1440843 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.1426. Min Act: -0.0000

Data Index: 1432002 (Python Code)

Max Activating Token Index: 943

Text #15

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.9920. Min Act: -0.0000

Data Index: 1553452 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.2653. Min Act: -0.0000

Data Index: 1563852 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.9818. Min Act: -0.0000

Data Index: 1537103 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 4.0483. Min Range: -4.0483

Max Act: 2.9646. Min Act: -0.0000

Data Index: 1488191 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.0939. Min Act: -0.0001

Data Index: 1437035 (Python Code)

Max Activating Token Index: 902