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

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

Neuron 1004 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.9448. Min Act: -0.0002

Data Index: 623856 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.9115. Min Act: -0.0002

Data Index: 373311 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.9149. Min Act: -0.0002

Data Index: 133711 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8973. Min Act: -0.0002

Data Index: 1213676 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8910. Min Act: -0.0002

Data Index: 1008297 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.9087. Min Act: -0.0002

Data Index: 47348 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8815. Min Act: -0.0002

Data Index: 866390 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8707. Min Act: -0.0002

Data Index: 1204869 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8530. Min Act: -0.0003

Data Index: 639553 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8688. Min Act: -0.0002

Data Index: 450315 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8338. Min Act: -0.0002

Data Index: 181966 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8350. Min Act: -0.0002

Data Index: 578352 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8377. Min Act: -0.0002

Data Index: 1102813 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8500. Min Act: -0.0002

Data Index: 1351220 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8214. Min Act: -0.0002

Data Index: 77988 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8140. Min Act: -0.0002

Data Index: 519561 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8129. Min Act: -0.0003

Data Index: 974900 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8224. Min Act: -0.0002

Data Index: 1050202 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8257. Min Act: -0.0003

Data Index: 342441 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.9448. Min Range: -0.9448

Max Act: 0.8100. Min Act: -0.0002

Data Index: 1208940 (C4 (Web Text))

Max Activating Token Index: 638