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

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

Neuron 4836 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1479714 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1419080 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1524470 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1412815 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1445226 (Python Code)

Max Activating Token Index: 374

Text #5

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1490727 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1380954 (Python Code)

Max Activating Token Index: 472

Text #7

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1514099 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1652520 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1601225 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1430448 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4224. Min Act: -0.0000

Data Index: 810436 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1616870 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1648966 (Python Code)

Max Activating Token Index: 995

Text #14

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1617558 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1417075 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1430585 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4918. Min Act: 0.0000

Data Index: 1610789 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4634. Min Act: -0.0000

Data Index: 458211 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1418048 (Python Code)

Max Activating Token Index: 90