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

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

Neuron 612 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2451. Min Act: -0.0001

Data Index: 1623318 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2284. Min Act: -0.0001

Data Index: 1490447 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2114. Min Act: -0.0001

Data Index: 1442495 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.0501. Min Act: -0.0001

Data Index: 1470593 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.3322. Min Act: -0.0001

Data Index: 1483875 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.9330. Min Act: -0.0001

Data Index: 1519398 (Python Code)

Max Activating Token Index: 579

Text #6

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.0587. Min Act: -0.0001

Data Index: 1590063 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.2221. Min Act: -0.0001

Data Index: 1421368 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.0492. Min Act: -0.0001

Data Index: 1617455 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.0384. Min Act: -0.0001

Data Index: 1537239 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1847. Min Act: -0.0001

Data Index: 1640164 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.8172. Min Act: -0.0001

Data Index: 1641645 (Python Code)

Max Activating Token Index: 205

Text #12

Max Range: 5.3322. Min Range: -5.3322

Max Act: 5.1638. Min Act: -0.0001

Data Index: 1653616 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.9910. Min Act: -0.0001

Data Index: 1368169 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.9468. Min Act: -0.0001

Data Index: 1451894 (Python Code)

Max Activating Token Index: 322

Text #15

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.9430. Min Act: -0.0001

Data Index: 1370275 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.9218. Min Act: -0.0001

Data Index: 1617468 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.7642. Min Act: -0.0001

Data Index: 1480289 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.7015. Min Act: -0.0001

Data Index: 1519732 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 5.3322. Min Range: -5.3322

Max Act: 4.5418. Min Act: -0.0001

Data Index: 1596710 (Python Code)

Max Activating Token Index: 400