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

Dataset: The Pile

Neuron 2120 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.4697. Min Act: -0.0000

Data Index: 1984455 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.4485. Min Act: -0.0000

Data Index: 949905 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1052731 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.3339. Min Act: -0.0000

Data Index: 834000 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1761819 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.2150. Min Act: -0.0000

Data Index: 106722 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1444233 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1894. Min Act: -0.0000

Data Index: 64585 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.3556. Min Act: -0.0000

Data Index: 408682 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1572725 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1293321 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1464. Min Act: -0.0000

Data Index: 658307 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.2167. Min Act: -0.0000

Data Index: 633348 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1358. Min Act: -0.0000

Data Index: 969270 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1445. Min Act: -0.0000

Data Index: 366956 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1857. Min Act: -0.0000

Data Index: 120478 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1066. Min Act: -0.0000

Data Index: 808134 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.2368. Min Act: -0.0000

Data Index: 245782 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1780546 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 1.4697. Min Range: -1.4697

Max Act: 1.0979. Min Act: -0.0000

Data Index: 231975 (The Pile)

Max Activating Token Index: 536