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

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

Neuron 4058 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: 1.0386. Min Range: -1.0386

Max Act: 1.0386. Min Act: -0.0000

Data Index: 681541 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.0386. Min Range: -1.0386

Max Act: 1.0151. Min Act: -0.0000

Data Index: 635275 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1214090 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9911. Min Act: -0.0000

Data Index: 524807 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9426. Min Act: -0.0000

Data Index: 583357 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9377. Min Act: -0.0000

Data Index: 194789 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9091. Min Act: -0.0000

Data Index: 127338 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8999. Min Act: -0.0000

Data Index: 350732 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9260. Min Act: -0.0000

Data Index: 954356 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.9095. Min Act: -0.0000

Data Index: 764304 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1181562 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8914. Min Act: -0.0000

Data Index: 40521 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8667. Min Act: -0.0000

Data Index: 48018 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8930. Min Act: -0.0000

Data Index: 826895 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8865. Min Act: -0.0000

Data Index: 583452 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1203481 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8361. Min Act: -0.0000

Data Index: 458466 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8285. Min Act: -0.0000

Data Index: 747277 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8477. Min Act: -0.0000

Data Index: 84017 (C4 (Web Text))

Max Activating Token Index: 733