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

Dataset: The Pile

Neuron 2585 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: 1.4295. Min Range: -1.4295

Max Act: 1.4295. Min Act: -0.0000

Data Index: 967758 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3104. Min Act: -0.0000

Data Index: 994239 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2825. Min Act: -0.0000

Data Index: 548523 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2059. Min Act: -0.0000

Data Index: 580824 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1565181 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.3160. Min Act: -0.0000

Data Index: 789141 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1432961 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1448004 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0886. Min Act: -0.0000

Data Index: 851355 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1469287 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1916141 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1091539 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1079854 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1316926 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1930449 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1568787 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1924056 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 1.4295. Min Range: -1.4295

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1312239 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.4295. Min Range: -1.4295

Max Act: 0.9745. Min Act: -0.0000

Data Index: 586799 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.4295. Min Range: -1.4295

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1975604 (The Pile)

Max Activating Token Index: 268