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

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

Neuron 4011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.6945. Min Act: -0.0000

Data Index: 785166 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1336228 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.4812. Min Act: -0.0000

Data Index: 603340 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1259732 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.3862. Min Act: -0.0000

Data Index: 853511 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.4322. Min Act: -0.0000

Data Index: 657841 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2529. Min Act: -0.0000

Data Index: 111185 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.3792. Min Act: -0.0000

Data Index: 690372 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2944. Min Act: -0.0000

Data Index: 304112 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.3690. Min Act: -0.0000

Data Index: 417268 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1010935 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2685. Min Act: -0.0000

Data Index: 531650 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.4191. Min Act: -0.0000

Data Index: 838910 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.1766. Min Act: -0.0000

Data Index: 964109 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1219095 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1256217 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1185476 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2183. Min Act: -0.0000

Data Index: 847967 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2019. Min Act: -0.0000

Data Index: 628124 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.6945. Min Range: -1.6945

Max Act: 1.2032. Min Act: -0.0000

Data Index: 812599 (C4 (Web Text))

Max Activating Token Index: 971