Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 77 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3554. Min Act: -0.0000

Data Index: 206820 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3155. Min Act: -0.0001

Data Index: 778578 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2982. Min Act: -0.0001

Data Index: 812164 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3317. Min Act: -0.0001

Data Index: 896632 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1266112 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1278136 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2905. Min Act: -0.0000

Data Index: 918119 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2758. Min Act: -0.0001

Data Index: 1258775 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2608. Min Act: -0.0000

Data Index: 991936 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1315454 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2780. Min Act: -0.0001

Data Index: 535554 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2762. Min Act: -0.0001

Data Index: 648038 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2809. Min Act: -0.0001

Data Index: 551589 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2631. Min Act: -0.0000

Data Index: 410956 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1000459 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2663. Min Act: -0.0001

Data Index: 530907 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2651. Min Act: -0.0001

Data Index: 214505 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2645. Min Act: -0.0000

Data Index: 580147 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2471. Min Act: -0.0001

Data Index: 471027 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2467. Min Act: -0.0001

Data Index: 186398 (C4 (Web Text))

Max Activating Token Index: 151