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

Dataset: The Pile

Neuron 891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.4503. Min Act: -0.0000

Data Index: 659257 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1983648 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1994. Min Act: -0.0000

Data Index: 931691 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2936. Min Act: -0.0000

Data Index: 698781 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1808891 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2829. Min Act: -0.0000

Data Index: 640252 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1582777 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1071660 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1805967 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1642182 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2300. Min Act: -0.0000

Data Index: 1902522 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1375. Min Act: -0.0000

Data Index: 460159 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1516. Min Act: -0.0000

Data Index: 989779 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1944501 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1153600 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1018896 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1135360 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1737. Min Act: -0.0000

Data Index: 892751 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.2494. Min Act: -0.0000

Data Index: 722506 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.4503. Min Range: -1.4503

Max Act: 1.1110. Min Act: -0.0000

Data Index: 214144 (The Pile)

Max Activating Token Index: 560