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

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

Neuron 4800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.8534. Min Act: -0.0000

Data Index: 1513516 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.8773. Min Act: -0.0000

Data Index: 1612654 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.6036. Min Act: -0.0000

Data Index: 1416194 (Python Code)

Max Activating Token Index: 569

Text #3

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.4921. Min Act: -0.0000

Data Index: 1478397 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.3330. Min Act: -0.0000

Data Index: 1608980 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.4544. Min Act: -0.0000

Data Index: 1530222 (Python Code)

Max Activating Token Index: 525

Text #6

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.2225. Min Act: -0.0000

Data Index: 1625276 (Python Code)

Max Activating Token Index: 348

Text #7

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.1876. Min Act: -0.0000

Data Index: 1571210 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.1366. Min Act: -0.0000

Data Index: 1583284 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.1073. Min Act: -0.0000

Data Index: 1379052 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.1726. Min Act: -0.0000

Data Index: 1399669 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 2.8773. Min Range: -2.8773

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1618281 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.1674. Min Act: -0.0000

Data Index: 1505889 (Python Code)

Max Activating Token Index: 438

Text #13

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.0185. Min Act: -0.0000

Data Index: 1396919 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.1924. Min Act: -0.0000

Data Index: 1381523 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 2.8773. Min Range: -2.8773

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1374384 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 2.8773. Min Range: -2.8773

Max Act: 1.8843. Min Act: -0.0000

Data Index: 1597778 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 2.8773. Min Range: -2.8773

Max Act: 2.0363. Min Act: -0.0000

Data Index: 1551243 (Python Code)

Max Activating Token Index: 137

Text #18

Max Range: 2.8773. Min Range: -2.8773

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1569564 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 2.8773. Min Range: -2.8773

Max Act: 1.7836. Min Act: -0.0000

Data Index: 1649941 (Python Code)

Max Activating Token Index: 276