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

Dataset: The Pile

Neuron 3855 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.1028. Min Act: -0.0000

Data Index: 813 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1181725 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0217. Min Act: -0.0000

Data Index: 57600 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1566751 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9561. Min Act: -0.0000

Data Index: 712288 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1439077 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9651. Min Act: -0.0000

Data Index: 445838 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1542223 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1970645 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1858596 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9947. Min Act: -0.0000

Data Index: 288664 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9320. Min Act: -0.0000

Data Index: 30454 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9287. Min Act: -0.0000

Data Index: 553256 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9208. Min Act: -0.0000

Data Index: 390281 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1375896 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9126. Min Act: -0.0000

Data Index: 450048 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9445. Min Act: -0.0000

Data Index: 12959 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1668304 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1271997 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1270153 (The Pile)

Max Activating Token Index: 409