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

Dataset: The Pile

Neuron 3783 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1900806 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1744128 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1574. Min Act: -0.0000

Data Index: 158136 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1118728 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1579. Min Act: -0.0000

Data Index: 439674 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1269595 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1127361 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1222. Min Act: -0.0000

Data Index: 346406 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1527. Min Act: -0.0000

Data Index: 221835 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1030188 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1161. Min Act: -0.0000

Data Index: 627600 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1082475 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1236. Min Act: -0.0000

Data Index: 623130 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1262. Min Act: -0.0000

Data Index: 975044 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1179. Min Act: -0.0000

Data Index: 425209 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1353. Min Act: -0.0000

Data Index: 357647 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1690289 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1022480 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1262. Min Act: -0.0000

Data Index: 287350 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1655581 (The Pile)

Max Activating Token Index: 810