Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2062 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3390. Min Act: -0.0000

Data Index: 567086 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1083793 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2766. Min Act: -0.0001

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2391. Min Act: -0.0001

Data Index: 390881 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2422. Min Act: -0.0001

Data Index: 115793 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2203. Min Act: -0.0000

Data Index: 179206 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2322. Min Act: 0.0000

Data Index: 1167677 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2358. Min Act: -0.0001

Data Index: 794632 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2312. Min Act: -0.0001

Data Index: 3531 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2176. Min Act: -0.0001

Data Index: 824756 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2282. Min Act: 0.0001

Data Index: 468413 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1115020 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2233. Min Act: -0.0001

Data Index: 800086 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1220288 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2143. Min Act: 0.0001

Data Index: 846960 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1218865 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2196. Min Act: -0.0001

Data Index: 656100 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2196. Min Act: -0.0001

Data Index: 219506 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1072599 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2037. Min Act: -0.0001

Data Index: 513163 (C4 (Web Text))

Max Activating Token Index: 945