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

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

Neuron 1002 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.4645. Min Act: -0.0000

Data Index: 1628666 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.5120. Min Act: -0.0000

Data Index: 1486818 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.1401. Min Act: -0.0000

Data Index: 1646238 (Python Code)

Max Activating Token Index: 696

Text #3

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.3377. Min Act: -0.0000

Data Index: 1370982 (Python Code)

Max Activating Token Index: 802

Text #4

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.3179. Min Act: -0.0000

Data Index: 1400835 (Python Code)

Max Activating Token Index: 553

Text #5

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.3136. Min Act: -0.0000

Data Index: 1455877 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.1866. Min Act: -0.0000

Data Index: 1417084 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.3004. Min Act: -0.0000

Data Index: 1425075 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.4201. Min Act: -0.0000

Data Index: 1496315 (Python Code)

Max Activating Token Index: 732

Text #9

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1630333 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.2862. Min Act: -0.0000

Data Index: 1562813 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.1469. Min Act: -0.0000

Data Index: 1362497 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1504615 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.2350. Min Act: -0.0000

Data Index: 1515898 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1645868 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.0909. Min Act: -0.0000

Data Index: 1446102 (Python Code)

Max Activating Token Index: 328

Text #16

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.0773. Min Act: -0.0000

Data Index: 1543507 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 2.5120. Min Range: -2.5120

Max Act: 1.9412. Min Act: -0.0000

Data Index: 1578545 (Python Code)

Max Activating Token Index: 910

Text #18

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.0385. Min Act: -0.0000

Data Index: 1435615 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 2.5120. Min Range: -2.5120

Max Act: 2.1670. Min Act: -0.0000

Data Index: 1640967 (Python Code)

Max Activating Token Index: 325