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

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

Neuron 3855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5653. Min Act: -0.0002

Data Index: 535 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5687. Min Act: -0.0002

Data Index: 779080 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5113. Min Act: -0.0002

Data Index: 1294004 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5336. Min Act: -0.0002

Data Index: 471828 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4930. Min Act: -0.0002

Data Index: 385594 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5252. Min Act: -0.0002

Data Index: 625269 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4874. Min Act: -0.0002

Data Index: 527677 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4986. Min Act: -0.0002

Data Index: 473615 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5116. Min Act: -0.0002

Data Index: 770878 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4981. Min Act: -0.0002

Data Index: 675525 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5025. Min Act: -0.0002

Data Index: 37242 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5162. Min Act: -0.0002

Data Index: 385187 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5244. Min Act: -0.0002

Data Index: 439043 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4951. Min Act: -0.0002

Data Index: 703579 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5119. Min Act: -0.0002

Data Index: 981203 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5447. Min Act: -0.0002

Data Index: 368550 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4874. Min Act: -0.0002

Data Index: 1318829 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4728. Min Act: -0.0002

Data Index: 147804 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4983. Min Act: -0.0002

Data Index: 164140 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4883. Min Act: -0.0002

Data Index: 1344953 (C4 (Web Text))

Max Activating Token Index: 748