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

Dataset: The Pile

Neuron 3479 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: 0.4571. Min Range: -0.4571

Max Act: 0.4571. Min Act: -0.0000

Data Index: 161873 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1854576 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.4177. Min Act: -0.0000

Data Index: 671933 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1546405 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.4194. Min Act: -0.0000

Data Index: 639935 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1740600 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1266212 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3630. Min Act: -0.0000

Data Index: 850183 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1288333 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3655. Min Act: -0.0000

Data Index: 842258 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3178. Min Act: -0.0000

Data Index: 352491 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3822. Min Act: -0.0000

Data Index: 781570 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1107709 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3237. Min Act: -0.0000

Data Index: 29627 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3060. Min Act: -0.0000

Data Index: 805843 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1841993 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1437718 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3545. Min Act: -0.0000

Data Index: 918900 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.2627. Min Act: -0.0000

Data Index: 678208 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.4571. Min Range: -0.4571

Max Act: 0.3267. Min Act: -0.0000

Data Index: 28892 (The Pile)

Max Activating Token Index: 950