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

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

Neuron 3817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8704. Min Range: -2.8704

Max Act: 2.8704. Min Act: -0.0000

Data Index: 1367028 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 2.8704. Min Range: -2.8704

Max Act: 2.7778. Min Act: -0.0000

Data Index: 1610125 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 2.8704. Min Range: -2.8704

Max Act: 2.4572. Min Act: -0.0000

Data Index: 1547271 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 2.8704. Min Range: -2.8704

Max Act: 2.1352. Min Act: -0.0000

Data Index: 1531654 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.9390. Min Act: -0.0000

Data Index: 1648942 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 2.8704. Min Range: -2.8704

Max Act: 2.0192. Min Act: -0.0000

Data Index: 1469087 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1643561 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 2.8704. Min Range: -2.8704

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1561428 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.8286. Min Act: -0.0000

Data Index: 1517315 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1372279 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.8470. Min Act: -0.0000

Data Index: 1651002 (Python Code)

Max Activating Token Index: 702

Text #11

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.6445. Min Act: -0.0000

Data Index: 1642523 (Python Code)

Max Activating Token Index: 99

Text #12

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1640315 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1504892 (Python Code)

Max Activating Token Index: 481

Text #14

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1642079 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.4936. Min Act: -0.0000

Data Index: 1368115 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1654681 (Python Code)

Max Activating Token Index: 1013

Text #17

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1453509 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1494845 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 2.8704. Min Range: -2.8704

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1590699 (Python Code)

Max Activating Token Index: 430