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

Dataset: The Pile

Neuron 675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.9756. Min Act: -0.0000

Data Index: 1236491 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 5.1444. Min Range: -5.1444

Max Act: 5.1444. Min Act: -0.0000

Data Index: 923467 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.8622. Min Act: -0.0000

Data Index: 898400 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5445. Min Act: -0.0000

Data Index: 1526864 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4888. Min Act: -0.0000

Data Index: 355303 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4706. Min Act: -0.0000

Data Index: 35042 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.7699. Min Act: -0.0000

Data Index: 1860539 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.4168. Min Act: -0.0000

Data Index: 602111 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.6031. Min Act: -0.0000

Data Index: 1244658 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.5016. Min Act: -0.0000

Data Index: 1122911 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.3066. Min Act: -0.0000

Data Index: 1389695 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.2631. Min Act: -0.0000

Data Index: 1638404 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.2310. Min Act: -0.0000

Data Index: 1701306 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.2047. Min Act: -0.0000

Data Index: 751135 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.1760. Min Act: -0.0000

Data Index: 1219302 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.3231. Min Act: -0.0000

Data Index: 1798370 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.1542. Min Act: -0.0000

Data Index: 1792961 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.1010. Min Act: -0.0000

Data Index: 1106480 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 5.1444. Min Range: -5.1444

Max Act: 4.0340. Min Act: -0.0000

Data Index: 569482 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 5.1444. Min Range: -5.1444

Max Act: 3.8542. Min Act: -0.0000

Data Index: 1308721 (The Pile)

Max Activating Token Index: 743