Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 857 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5974. Min Act: -0.0003

Data Index: 58104 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5555. Min Act: -0.0003

Data Index: 461374 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4449. Min Act: -0.0003

Data Index: 32019 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4453. Min Act: -0.0003

Data Index: 1316504 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4349. Min Act: -0.0003

Data Index: 239919 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4706. Min Act: -0.0003

Data Index: 1284293 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5325. Min Act: -0.0003

Data Index: 1228698 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4942. Min Act: -0.0003

Data Index: 234613 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4309. Min Act: -0.0003

Data Index: 1086865 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4705. Min Act: -0.0003

Data Index: 67838 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3682. Min Act: -0.0003

Data Index: 1172392 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4450. Min Act: -0.0003

Data Index: 1291745 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4386. Min Act: -0.0003

Data Index: 708267 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4322. Min Act: -0.0003

Data Index: 446671 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4251. Min Act: -0.0003

Data Index: 355267 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4407. Min Act: -0.0003

Data Index: 415879 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4247. Min Act: -0.0003

Data Index: 886690 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3728. Min Act: -0.0003

Data Index: 148861 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4368. Min Act: -0.0003

Data Index: 682314 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3780. Min Act: -0.0003

Data Index: 1079717 (C4 (Web Text))

Max Activating Token Index: 397