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

Dataset: The Pile

Neuron 17 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: 0.4749. Min Range: -0.4749

Max Act: 0.4454. Min Act: -0.0000

Data Index: 720787 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.4335. Min Act: -0.0000

Data Index: 705670 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3822. Min Act: 0.0000

Data Index: 1421698 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.4749. Min Act: -0.0000

Data Index: 728964 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1538360 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3329. Min Act: -0.0000

Data Index: 643560 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3486. Min Act: -0.0000

Data Index: 457120 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1848031 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3364. Min Act: 0.0000

Data Index: 517169 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1803933 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3226. Min Act: -0.0000

Data Index: 549937 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3167. Min Act: -0.0000

Data Index: 997228 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3240. Min Act: 0.0000

Data Index: 528679 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.2777. Min Act: 0.0000

Data Index: 1401569 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3120. Min Act: -0.0000

Data Index: 771227 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1584007 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.2925. Min Act: 0.0000

Data Index: 1431315 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1601945 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.2418. Min Act: -0.0000

Data Index: 262355 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.4749. Min Range: -0.4749

Max Act: 0.2975. Min Act: -0.0000

Data Index: 502733 (The Pile)

Max Activating Token Index: 864