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

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

Neuron 860 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: 0.7429. Min Range: -0.7429

Max Act: 0.7429. Min Act: -0.0000

Data Index: 259899 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.6523. Min Act: -0.0000

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.6553. Min Act: -0.0000

Data Index: 805859 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.6281. Min Act: -0.0000

Data Index: 239531 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1088134 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4979. Min Act: -0.0000

Data Index: 122467 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.5540. Min Act: -0.0000

Data Index: 258272 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4993. Min Act: -0.0000

Data Index: 686717 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4926. Min Act: -0.0000

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4575. Min Act: -0.0000

Data Index: 715650 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4818. Min Act: -0.0000

Data Index: 181424 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4255. Min Act: -0.0000

Data Index: 761448 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1211638 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4609. Min Act: -0.0000

Data Index: 854474 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1315812 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4392. Min Act: -0.0000

Data Index: 149279 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4535. Min Act: -0.0000

Data Index: 440927 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1145493 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.3939. Min Act: -0.0000

Data Index: 657352 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.7429. Min Range: -0.7429

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1097593 (C4 (Web Text))

Max Activating Token Index: 909