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

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

Neuron 370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1425084 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2338. Min Act: -0.0001

Data Index: 1652261 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1646964 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1470037 (Python Code)

Max Activating Token Index: 406

Text #4

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1569235 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1554217 (Python Code)

Max Activating Token Index: 361

Text #6

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1370839 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2062. Min Act: -0.0001

Data Index: 1611992 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2121. Min Act: -0.0001

Data Index: 1608851 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1403817 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1948. Min Act: -0.0001

Data Index: 1566011 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1480545 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1516351 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1472009 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1478236 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1555633 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1651236 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1637553 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1478398 (Python Code)

Max Activating Token Index: 302

Text #19

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1461011 (Python Code)

Max Activating Token Index: 201