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

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

Neuron 1654 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1475854 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1377106 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1515312 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1418909 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1363542 (Python Code)

Max Activating Token Index: 686

Text #5

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1510957 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1646382 (Python Code)

Max Activating Token Index: 607

Text #7

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1467571 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1580799 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1408527 (Python Code)

Max Activating Token Index: 256

Text #10

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1635451 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1604615 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1563193 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1605099 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1445563 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1581110 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1603045 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1394764 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1639244 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 0.4237. Min Range: -0.4237

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1436434 (Python Code)

Max Activating Token Index: 946