Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 904 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0453. Min Act: -0.0001

Data Index: 124057 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0438. Min Act: -0.0001

Data Index: 983181 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0000

Data Index: 999208 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1338256 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1278665 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0453. Min Act: -0.0001

Data Index: 249665 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0379. Min Act: -0.0000

Data Index: 838104 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0407. Min Act: -0.0001

Data Index: 111046 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0415. Min Act: -0.0001

Data Index: 976304 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0406. Min Act: -0.0001

Data Index: 302190 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0404. Min Act: -0.0001

Data Index: 785114 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1514796 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0389. Min Act: -0.0001

Data Index: 227621 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0405. Min Act: -0.0001

Data Index: 905957 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0407. Min Act: -0.0001

Data Index: 245527 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0397. Min Act: -0.0001

Data Index: 283928 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1339976 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0385. Min Act: -0.0001

Data Index: 6384 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0401. Min Act: -0.0001

Data Index: 146161 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1245601 (C4 (Web Text))

Max Activating Token Index: 87