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

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

Neuron 3139 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0003

Data Index: 831177 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0553. Min Act: -0.0003

Data Index: 80586 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1119570 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0477. Min Act: -0.0002

Data Index: 775875 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1105048 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0445. Min Act: -0.0003

Data Index: 618704 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0438. Min Act: -0.0003

Data Index: 803220 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1288202 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0429. Min Act: -0.0003

Data Index: 416824 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0418. Min Act: -0.0003

Data Index: 126639 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0420. Min Act: -0.0003

Data Index: 655007 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1000228 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0413. Min Act: -0.0002

Data Index: 243100 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1054779 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0380. Min Act: -0.0003

Data Index: 697265 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1105714 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0391. Min Act: -0.0002

Data Index: 678671 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0375. Min Act: -0.0002

Data Index: 762132 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0357. Min Act: -0.0003

Data Index: 367998 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0375. Min Act: -0.0003

Data Index: 83673 (C4 (Web Text))

Max Activating Token Index: 91