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

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

Neuron 4971 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2666. Min Act: -0.0000

Data Index: 872121 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1003475 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2823. Min Act: -0.0000

Data Index: 896486 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2721. Min Act: -0.0000

Data Index: 90614 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2426. Min Act: -0.0000

Data Index: 308053 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1169252 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2265. Min Act: -0.0000

Data Index: 435305 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2359. Min Act: -0.0000

Data Index: 937696 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1139478 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1042545 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2361. Min Act: -0.0000

Data Index: 561978 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2327. Min Act: -0.0000

Data Index: 970714 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2234. Min Act: -0.0000

Data Index: 815081 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2245. Min Act: -0.0000

Data Index: 393108 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1057256 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2215. Min Act: -0.0000

Data Index: 151109 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2280. Min Act: -0.0000

Data Index: 444557 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2205. Min Act: -0.0000

Data Index: 766247 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1324046 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2176. Min Act: -0.0000

Data Index: 749058 (C4 (Web Text))

Max Activating Token Index: 1009