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

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

Neuron 1147 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: 0.7780. Min Range: -0.7780

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1384846 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1408658 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1517047 (Python Code)

Max Activating Token Index: 901

Text #3

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1426796 (Python Code)

Max Activating Token Index: 770

Text #4

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1537636 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1514587 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1379965 (Python Code)

Max Activating Token Index: 270

Text #7

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1519357 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1540434 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1554762 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1605352 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1543559 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1454929 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1492791 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1547667 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1505420 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1384871 (Python Code)

Max Activating Token Index: 435

Text #17

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1405463 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1579446 (Python Code)

Max Activating Token Index: 619

Text #19

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1447438 (Python Code)

Max Activating Token Index: 903