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

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

Neuron 3334 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3423. Min Act: -0.0003

Data Index: 1490377 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3408. Min Act: -0.0002

Data Index: 1393722 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3312. Min Act: -0.0002

Data Index: 1543108 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2985. Min Act: -0.0003

Data Index: 1374177 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.3023. Min Act: -0.0003

Data Index: 1606694 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2853. Min Act: -0.0002

Data Index: 1425226 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2678. Min Act: -0.0003

Data Index: 1443752 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2575. Min Act: -0.0003

Data Index: 1557928 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2584. Min Act: -0.0003

Data Index: 1587805 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2586. Min Act: -0.0003

Data Index: 1477481 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2627. Min Act: -0.0003

Data Index: 1443867 (Python Code)

Max Activating Token Index: 161

Text #11

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2527. Min Act: -0.0002

Data Index: 1516596 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2507. Min Act: -0.0003

Data Index: 1519842 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2420. Min Act: -0.0002

Data Index: 1600374 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2587. Min Act: -0.0003

Data Index: 1531177 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2448. Min Act: -0.0002

Data Index: 1646174 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2538. Min Act: -0.0002

Data Index: 1525293 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2376. Min Act: -0.0002

Data Index: 1566368 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2389. Min Act: -0.0002

Data Index: 1472042 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 0.3423. Min Range: -0.3423

Max Act: 0.2450. Min Act: -0.0003

Data Index: 1417172 (Python Code)

Max Activating Token Index: 611