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

Dataset: The Pile

Neuron 230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2416. Min Act: -0.0000

Data Index: 334087 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1830105 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2357. Min Act: -0.0000

Data Index: 349031 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2432. Min Act: -0.0000

Data Index: 756415 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1892045 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1564464 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1221936 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1710677 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1204248 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1667929 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2167. Min Act: -0.0000

Data Index: 606419 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1127455 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1582225 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2143. Min Act: -0.0000

Data Index: 441352 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1728752 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2046. Min Act: -0.0000

Data Index: 435875 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2124. Min Act: -0.0000

Data Index: 451097 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2095. Min Act: -0.0000

Data Index: 219702 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1452105 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1642905 (The Pile)

Max Activating Token Index: 82