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

Dataset: The Pile

Neuron 2310 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: 0.4199. Min Range: -0.4199

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1857768 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.3247. Min Act: -0.0000

Data Index: 69484 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2660. Min Act: -0.0000

Data Index: 145232 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1199272 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2656. Min Act: -0.0000

Data Index: 515853 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1768232 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1912583 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1180904 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1899950 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1472879 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1881535 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2210. Min Act: -0.0000

Data Index: 294744 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1404499 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1742174 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2222. Min Act: -0.0000

Data Index: 247019 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2148. Min Act: -0.0000

Data Index: 354742 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1845751 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1041283 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1542222 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.4199. Min Range: -0.4199

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1580900 (The Pile)

Max Activating Token Index: 722