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

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

Neuron 2018 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.8809. Min Act: -0.0000

Data Index: 729931 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6922. Min Act: -0.0000

Data Index: 847801 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6395. Min Act: -0.0000

Data Index: 675894 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.6388. Min Act: -0.0000

Data Index: 406503 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5726. Min Act: 0.0000

Data Index: 548761 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5872. Min Act: -0.0000

Data Index: 615920 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5698. Min Act: -0.0000

Data Index: 334763 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5656. Min Act: -0.0000

Data Index: 386365 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1136689 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5651. Min Act: -0.0000

Data Index: 500028 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5404. Min Act: -0.0000

Data Index: 420690 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5147. Min Act: -0.0000

Data Index: 341595 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5322. Min Act: -0.0000

Data Index: 119617 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5106. Min Act: -0.0000

Data Index: 467639 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5731. Min Act: 0.0002

Data Index: 277578 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5100. Min Act: -0.0000

Data Index: 619639 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.4962. Min Act: -0.0000

Data Index: 889745 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1142777 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.4705. Min Act: -0.0000

Data Index: 934916 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.8809. Min Range: -0.8809

Max Act: 0.5091. Min Act: -0.0000

Data Index: 186656 (C4 (Web Text))

Max Activating Token Index: 754