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

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

Neuron 4422 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: 0.1449. Min Range: -0.1449

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1498249 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1588456 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1242. Min Act: -0.0001

Data Index: 783920 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1378741 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1300. Min Act: -0.0001

Data Index: 947337 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1223. Min Act: -0.0001

Data Index: 640034 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1243. Min Act: -0.0001

Data Index: 881773 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1164. Min Act: -0.0001

Data Index: 994140 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1271630 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1152. Min Act: -0.0001

Data Index: 936808 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1197. Min Act: -0.0001

Data Index: 198244 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1250. Min Act: -0.0001

Data Index: 369907 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1070. Min Act: -0.0001

Data Index: 289643 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0815. Min Act: -0.0002

Data Index: 151929 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1232. Min Act: -0.0001

Data Index: 911122 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1460240 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1551665 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1239. Min Act: -0.0001

Data Index: 690573 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1078952 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1143495 (C4 (Web Text))

Max Activating Token Index: 52