Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5460 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.3259. Min Act: -0.0000

Data Index: 132753 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2409. Min Act: -0.0000

Data Index: 274202 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2240. Min Act: -0.0000

Data Index: 912303 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2237. Min Act: -0.0000

Data Index: 481197 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2213. Min Act: -0.0000

Data Index: 704553 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2222. Min Act: -0.0000

Data Index: 384340 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2309. Min Act: -0.0000

Data Index: 375131 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1313218 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2085. Min Act: -0.0000

Data Index: 660308 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2092. Min Act: -0.0000

Data Index: 879206 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1225773 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2041. Min Act: -0.0000

Data Index: 567284 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2110. Min Act: -0.0000

Data Index: 363044 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1179244 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2081. Min Act: -0.0000

Data Index: 556648 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2084. Min Act: -0.0000

Data Index: 858803 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2073. Min Act: -0.0000

Data Index: 293839 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.2046. Min Act: -0.0000

Data Index: 613998 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1024123 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.3259. Min Range: -0.3259

Max Act: 0.1967. Min Act: -0.0000

Data Index: 238977 (C4 (Web Text))

Max Activating Token Index: 613