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

Dataset: The Pile

Neuron 600 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: 1.4410. Min Range: -1.4410

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1331271 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3969. Min Act: -0.0000

Data Index: 724040 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1192493 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3734. Min Act: -0.0000

Data Index: 1532238 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1636254 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1831304 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1149614 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.3278. Min Act: -0.0000

Data Index: 52955 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1908485 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2152. Min Act: -0.0000

Data Index: 233138 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1252603 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1017318 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1234862 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2326. Min Act: -0.0000

Data Index: 535537 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1968144 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2181. Min Act: -0.0000

Data Index: 675426 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1840253 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.2259. Min Act: -0.0000

Data Index: 73015 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1743. Min Act: -0.0000

Data Index: 877167 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 1.4410. Min Range: -1.4410

Max Act: 1.1686. Min Act: -0.0000

Data Index: 786203 (The Pile)

Max Activating Token Index: 34