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

Dataset: The Pile

Neuron 3006 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: 1.6990. Min Range: -1.6990

Max Act: 1.6205. Min Act: -0.0000

Data Index: 519093 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.5958. Min Act: -0.0000

Data Index: 605461 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6568. Min Act: -0.0000

Data Index: 1139079 (The Pile)

Max Activating Token Index: 881

Text #3

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6990. Min Act: -0.0000

Data Index: 120372 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6654. Min Act: -0.0000

Data Index: 785959 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1306237 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6298. Min Act: -0.0000

Data Index: 991212 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.6613. Min Act: -0.0000

Data Index: 234827 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1806607 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1255958 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4144. Min Act: -0.0000

Data Index: 714165 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.5434. Min Act: -0.0000

Data Index: 785528 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4558. Min Act: -0.0000

Data Index: 490201 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.5414. Min Act: -0.0000

Data Index: 504821 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3387. Min Act: -0.0000

Data Index: 88271 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2372. Min Act: -0.0000

Data Index: 558256 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1447670 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4501. Min Act: -0.0000

Data Index: 899640 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1809258 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1059858 (The Pile)

Max Activating Token Index: 779