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

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

Neuron 725 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.7123. Min Act: -0.0001

Data Index: 876732 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.6027. Min Act: -0.0001

Data Index: 238419 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.7902. Min Act: -0.0001

Data Index: 100666 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.5756. Min Act: -0.0001

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.7217. Min Act: -0.0001

Data Index: 423138 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.3877. Min Act: -0.0001

Data Index: 726891 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.5815. Min Act: -0.0001

Data Index: 752426 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.7148. Min Act: -0.0001

Data Index: 1301738 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.6927. Min Act: -0.0001

Data Index: 876387 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.3934. Min Act: -0.0001

Data Index: 717716 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.5784. Min Act: -0.0001

Data Index: 1354497 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.5753. Min Act: -0.0001

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.4516. Min Act: -0.0001

Data Index: 1101137 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.4621. Min Act: -0.0001

Data Index: 859522 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.4469. Min Act: -0.0001

Data Index: 330326 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.2746. Min Act: -0.0001

Data Index: 165515 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.2939. Min Act: -0.0001

Data Index: 793114 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.6196. Min Act: -0.0001

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.6350. Min Act: -0.0000

Data Index: 1305584 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 3.7902. Min Range: -3.7902

Max Act: 3.5961. Min Act: -0.0001

Data Index: 1233763 (C4 (Web Text))

Max Activating Token Index: 938