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

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

Neuron 355 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: 0.8617. Min Range: -0.8617

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1551192 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1492574 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1427832 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1376278 (Python Code)

Max Activating Token Index: 469

Text #4

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1445467 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1510097 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1503106 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1629895 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1529557 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1509063 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1580801 (Python Code)

Max Activating Token Index: 753

Text #11

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1629635 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1450391 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1408129 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1479621 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5674. Min Act: -0.0000

Data Index: 135008 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1456862 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1460084 (Python Code)

Max Activating Token Index: 733

Text #18

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1617549 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 0.8617. Min Range: -0.8617

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1409661 (Python Code)

Max Activating Token Index: 560