Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1179 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2363. Min Act: -0.0001

Data Index: 51501 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2022. Min Act: -0.0001

Data Index: 980473 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1933. Min Act: -0.0001

Data Index: 304522 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1197. Min Act: -0.0001

Data Index: 601447 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1250. Min Act: -0.0001

Data Index: 28818 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1296. Min Act: -0.0001

Data Index: 433788 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1181. Min Act: -0.0001

Data Index: 173943 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1169. Min Act: -0.0001

Data Index: 595414 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1214. Min Act: -0.0001

Data Index: 810898 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1086. Min Act: -0.0001

Data Index: 883279 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1109. Min Act: -0.0001

Data Index: 640113 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1017. Min Act: -0.0001

Data Index: 297732 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1064. Min Act: -0.0001

Data Index: 109952 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.0987. Min Act: -0.0001

Data Index: 973416 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1015. Min Act: -0.0001

Data Index: 435984 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1013. Min Act: -0.0001

Data Index: 773475 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1286475 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.0997. Min Act: -0.0001

Data Index: 741922 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1028. Min Act: -0.0001

Data Index: 403187 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1335822 (C4 (Web Text))

Max Activating Token Index: 193