Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2613 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1466014 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1468900 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1632124 (Python Code)

Max Activating Token Index: 756

Text #3

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7907. Min Act: -0.0001

Data Index: 1569955 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1599641 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7486. Min Act: -0.0001

Data Index: 1382234 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1472963 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1433633 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6871. Min Act: -0.0001

Data Index: 1582272 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1632564 (Python Code)

Max Activating Token Index: 214

Text #10

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.7029. Min Act: -0.0001

Data Index: 1462098 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1388789 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1556782 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6518. Min Act: -0.0001

Data Index: 1598015 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1463430 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6806. Min Act: -0.0001

Data Index: 1415432 (Python Code)

Max Activating Token Index: 910

Text #16

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1569602 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1613690 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1443062 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 0.8218. Min Range: -0.8218

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1595680 (Python Code)

Max Activating Token Index: 572