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

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

Neuron 2534 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: 0.8270. Min Range: -0.8270

Max Act: 0.8270. Min Act: -0.0001

Data Index: 916862 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1062012 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1328720 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7822. Min Act: -0.0001

Data Index: 1179344 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7509. Min Act: -0.0001

Data Index: 1053293 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6805. Min Act: -0.0001

Data Index: 1349657 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6845. Min Act: -0.0001

Data Index: 119683 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7202. Min Act: -0.0000

Data Index: 892357 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7605. Min Act: -0.0001

Data Index: 1134328 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6583. Min Act: -0.0001

Data Index: 592111 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6935. Min Act: -0.0001

Data Index: 737721 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1300671 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6636. Min Act: -0.0001

Data Index: 1167618 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7025. Min Act: -0.0001

Data Index: 1277641 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6759. Min Act: -0.0001

Data Index: 558993 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6931. Min Act: -0.0001

Data Index: 895651 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6329. Min Act: -0.0001

Data Index: 620598 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6916. Min Act: -0.0001

Data Index: 1307872 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6491. Min Act: -0.0001

Data Index: 1118077 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1230320 (C4 (Web Text))

Max Activating Token Index: 185