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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1457 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1303624 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2602. Min Act: -0.0000

Data Index: 368652 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2483. Min Act: -0.0000

Data Index: 632933 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1033620 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2581. Min Act: -0.0000

Data Index: 880526 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1338174 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2287. Min Act: -0.0000

Data Index: 428289 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2303. Min Act: -0.0000

Data Index: 509222 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2265. Min Act: -0.0000

Data Index: 814185 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2247. Min Act: -0.0000

Data Index: 401528 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2178. Min Act: -0.0000

Data Index: 111025 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2235. Min Act: -0.0000

Data Index: 977283 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2131. Min Act: -0.0000

Data Index: 913224 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2267. Min Act: -0.0000

Data Index: 373829 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2136. Min Act: -0.0000

Data Index: 470273 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2119. Min Act: -0.0000

Data Index: 803629 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2286. Min Act: -0.0000

Data Index: 87010 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1200918 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.1834. Min Act: -0.0000

Data Index: 493450 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.2846. Min Range: -0.2846

Max Act: 0.2216. Min Act: -0.0000

Data Index: 944055 (C4 (Web Text))

Max Activating Token Index: 1020