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

Dataset: The Pile

Neuron 3547 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: 0.3507. Min Range: -0.3507

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1428028 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1508557 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1438646 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2449. Min Act: -0.0000

Data Index: 429778 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1829209 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2400. Min Act: -0.0000

Data Index: 454913 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1671742 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2322. Min Act: -0.0000

Data Index: 359831 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2377. Min Act: -0.0000

Data Index: 488446 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1332016 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2144. Min Act: -0.0000

Data Index: 600990 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1319158 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1883407 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1149155 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2031. Min Act: -0.0000

Data Index: 719499 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.1891. Min Act: -0.0000

Data Index: 326398 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2232. Min Act: -0.0000

Data Index: 797125 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.1995. Min Act: -0.0000

Data Index: 717339 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2211. Min Act: -0.0000

Data Index: 726261 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1747248 (The Pile)

Max Activating Token Index: 666