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

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

Neuron 4608 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: 0.6209. Min Range: -0.6209

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1172465 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5737. Min Act: -0.0000

Data Index: 628414 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5788. Min Act: -0.0000

Data Index: 684959 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.6209. Min Act: -0.0000

Data Index: 27931 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5799. Min Act: -0.0000

Data Index: 436771 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5466. Min Act: -0.0000

Data Index: 812218 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5855. Min Act: -0.0000

Data Index: 956157 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5239. Min Act: -0.0000

Data Index: 816241 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1283529 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1085141 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5149. Min Act: -0.0000

Data Index: 773898 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.5186. Min Act: -0.0000

Data Index: 368522 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1075538 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4865. Min Act: -0.0000

Data Index: 550736 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4761. Min Act: -0.0000

Data Index: 430853 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4948. Min Act: -0.0000

Data Index: 240661 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4340. Min Act: -0.0000

Data Index: 25185 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4391. Min Act: -0.0000

Data Index: 766671 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1327834 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.6209. Min Range: -0.6209

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1248958 (C4 (Web Text))

Max Activating Token Index: 585