Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0151. Min Act: -0.0000

Data Index: 739796 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0461. Min Act: -0.0000

Data Index: 941378 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8985. Min Act: -0.0000

Data Index: 660497 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8535. Min Act: -0.0000

Data Index: 537709 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8405. Min Act: -0.0000

Data Index: 37623 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1474301 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8626. Min Act: -0.0000

Data Index: 156982 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1244173 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1994288 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1557465 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1479715 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7441. Min Act: -0.0000

Data Index: 162391 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1810874 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1871333 (The Pile)

Max Activating Token Index: 305

Text #14

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1979615 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7573. Min Act: -0.0000

Data Index: 539586 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7218. Min Act: -0.0000

Data Index: 274329 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1820551 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1793036 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7191. Min Act: -0.0000

Data Index: 543409 (The Pile)

Max Activating Token Index: 198