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

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

Neuron 232 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.9621. Min Act: -0.0000

Data Index: 1476032 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.9273. Min Act: -0.0000

Data Index: 1394942 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.8110. Min Act: -0.0000

Data Index: 1604753 (Python Code)

Max Activating Token Index: 921

Text #3

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.8490. Min Act: -0.0000

Data Index: 1530355 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.6268. Min Act: -0.0000

Data Index: 1397481 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.7314. Min Act: -0.0000

Data Index: 1561387 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.7137. Min Act: -0.0000

Data Index: 1479023 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.6921. Min Act: -0.0000

Data Index: 1619076 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.6501. Min Act: -0.0000

Data Index: 1461606 (Python Code)

Max Activating Token Index: 910

Text #9

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.6197. Min Act: -0.0000

Data Index: 1645544 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.5964. Min Act: -0.0000

Data Index: 1606671 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.5123. Min Act: -0.0000

Data Index: 1617819 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.4754. Min Act: -0.0000

Data Index: 1442359 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.4548. Min Act: -0.0000

Data Index: 1387388 (Python Code)

Max Activating Token Index: 882

Text #14

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1500536 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.4398. Min Act: -0.0000

Data Index: 1496373 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.4131. Min Act: -0.0000

Data Index: 1406120 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.1431. Min Act: -0.0000

Data Index: 1630323 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.3770. Min Act: -0.0000

Data Index: 1621585 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 2.9621. Min Range: -2.9621

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1641870 (Python Code)

Max Activating Token Index: 645