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

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

Neuron 4816 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: 1.2866. Min Range: -1.2866

Max Act: 1.2380. Min Act: -0.0001

Data Index: 26305 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1854. Min Act: -0.0001

Data Index: 237156 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1529. Min Act: -0.0001

Data Index: 254432 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.2866. Min Act: -0.0001

Data Index: 1230389 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.2095. Min Act: -0.0001

Data Index: 92514 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.2033. Min Act: -0.0001

Data Index: 662738 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1610. Min Act: -0.0001

Data Index: 1238044 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1067834 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.0539. Min Act: -0.0001

Data Index: 721944 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.0506. Min Act: -0.0001

Data Index: 423592 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1696. Min Act: -0.0000

Data Index: 147504 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1766. Min Act: -0.0001

Data Index: 680806 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1769. Min Act: -0.0001

Data Index: 616571 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1332. Min Act: -0.0001

Data Index: 967570 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1206848 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1023. Min Act: -0.0001

Data Index: 1140835 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1462. Min Act: -0.0001

Data Index: 160091 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1147. Min Act: -0.0001

Data Index: 606543 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.0785. Min Act: -0.0001

Data Index: 393725 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.2866. Min Range: -1.2866

Max Act: 1.1455. Min Act: -0.0001

Data Index: 204303 (C4 (Web Text))

Max Activating Token Index: 865