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

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

Neuron 1729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1058473 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1277. Min Act: -0.0001

Data Index: 118613 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1009205 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1063. Min Act: -0.0000

Data Index: 880827 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1089. Min Act: -0.0000

Data Index: 421412 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1050. Min Act: -0.0001

Data Index: 470767 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0994. Min Act: -0.0000

Data Index: 171604 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0967. Min Act: -0.0001

Data Index: 674991 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0929. Min Act: -0.0001

Data Index: 598279 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1210712 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0879. Min Act: -0.0001

Data Index: 803740 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0947. Min Act: -0.0000

Data Index: 122329 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0905. Min Act: -0.0001

Data Index: 260673 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0925. Min Act: -0.0000

Data Index: 482445 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0923. Min Act: -0.0001

Data Index: 837813 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0992. Min Act: -0.0001

Data Index: 318354 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0915. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1296457 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0924. Min Act: -0.0001

Data Index: 702933 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0872. Min Act: -0.0000

Data Index: 122074 (C4 (Web Text))

Max Activating Token Index: 934