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

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

Neuron 5669 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1724. Min Act: -0.0000

Data Index: 619014 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1535. Min Act: -0.0000

Data Index: 374333 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1562. Min Act: -0.0000

Data Index: 826355 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1474. Min Act: -0.0000

Data Index: 277437 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1530. Min Act: -0.0000

Data Index: 557884 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1387998 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1005145 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1469. Min Act: -0.0000

Data Index: 229918 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1265. Min Act: -0.0000

Data Index: 780753 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1353. Min Act: -0.0000

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1100194 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1299. Min Act: -0.0000

Data Index: 720065 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1310. Min Act: -0.0000

Data Index: 502119 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1249. Min Act: -0.0000

Data Index: 637081 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1112. Min Act: -0.0000

Data Index: 568495 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1570355 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1291. Min Act: -0.0000

Data Index: 807146 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1256. Min Act: -0.0000

Data Index: 952803 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1207. Min Act: -0.0000

Data Index: 79066 (C4 (Web Text))

Max Activating Token Index: 243