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

Dataset: The Pile

Neuron 1445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1331924 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1661161 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1635576 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5110. Min Act: -0.0000

Data Index: 699042 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1006213 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4521. Min Act: -0.0000

Data Index: 486480 (The Pile)

Max Activating Token Index: 724

Text #6

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1177582 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4375. Min Act: -0.0000

Data Index: 897894 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1431018 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4330. Min Act: -0.0000

Data Index: 123301 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1087063 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4051. Min Act: -0.0000

Data Index: 837774 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4432. Min Act: -0.0000

Data Index: 709666 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1054909 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1798689 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4387. Min Act: -0.0000

Data Index: 990972 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4187. Min Act: -0.0000

Data Index: 451446 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1752330 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1676246 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1315250 (The Pile)

Max Activating Token Index: 153