Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2747 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.4413. Min Act: -0.0000

Data Index: 555368 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1185674 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.3335. Min Act: -0.0000

Data Index: 906105 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.3348. Min Act: -0.0000

Data Index: 902430 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.2586. Min Act: -0.0000

Data Index: 885756 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1430107 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1110113 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.2429. Min Act: -0.0000

Data Index: 526636 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1288577 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1501. Min Act: -0.0000

Data Index: 696580 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1506226 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1401162 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1605054 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1003837 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1244. Min Act: -0.0000

Data Index: 512323 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1376028 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1313185 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1375318 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1486141 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 1.4413. Min Range: -1.4413

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1646135 (Python Code)

Max Activating Token Index: 614