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

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

Neuron 2887 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1517128 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.3396. Min Act: -0.0000

Data Index: 1602613 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.2144. Min Act: -0.0000

Data Index: 1591429 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1530101 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.0591. Min Act: -0.0000

Data Index: 1469392 (Python Code)

Max Activating Token Index: 875

Text #5

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.8887. Min Act: -0.0000

Data Index: 1535070 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 2.4210. Min Range: -2.4210

Max Act: 2.0659. Min Act: -0.0000

Data Index: 1436928 (Python Code)

Max Activating Token Index: 872

Text #7

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.9307. Min Act: -0.0000

Data Index: 1575678 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.8892. Min Act: -0.0000

Data Index: 1407302 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.7550. Min Act: -0.0000

Data Index: 1545300 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.9478. Min Act: -0.0000

Data Index: 1644607 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1475623 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.8055. Min Act: -0.0000

Data Index: 1402418 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.9005. Min Act: -0.0000

Data Index: 1562511 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.8726. Min Act: -0.0000

Data Index: 1462051 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.7824. Min Act: -0.0000

Data Index: 1650809 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1438608 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1616138 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.7202. Min Act: -0.0000

Data Index: 1626109 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 2.4210. Min Range: -2.4210

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1488353 (Python Code)

Max Activating Token Index: 766