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

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

Neuron 4880 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0739. Min Range: -6.0739

Max Act: 6.0739. Min Act: -0.0000

Data Index: 1598134 (Python Code)

Max Activating Token Index: 337

Text #1

Max Range: 6.0739. Min Range: -6.0739

Max Act: 5.2566. Min Act: -0.0000

Data Index: 1561246 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 6.0739. Min Range: -6.0739

Max Act: 5.5605. Min Act: -0.0000

Data Index: 1432600 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 6.0739. Min Range: -6.0739

Max Act: 5.1282. Min Act: -0.0000

Data Index: 1436033 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 6.0739. Min Range: -6.0739

Max Act: 5.4737. Min Act: -0.0000

Data Index: 1396929 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 6.0739. Min Range: -6.0739

Max Act: 5.0096. Min Act: -0.0000

Data Index: 1413813 (Python Code)

Max Activating Token Index: 398

Text #6

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.9280. Min Act: -0.0000

Data Index: 1472597 (Python Code)

Max Activating Token Index: 929

Text #7

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.8060. Min Act: -0.0000

Data Index: 1460366 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 6.0739. Min Range: -6.0739

Max Act: 3.9255. Min Act: -0.0000

Data Index: 1648716 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.6363. Min Act: -0.0000

Data Index: 1454572 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.4143. Min Act: -0.0000

Data Index: 1426007 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.6990. Min Act: -0.0000

Data Index: 1363910 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.5257. Min Act: -0.0000

Data Index: 1512189 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.5154. Min Act: -0.0000

Data Index: 1440356 (Python Code)

Max Activating Token Index: 309

Text #14

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.5063. Min Act: -0.0000

Data Index: 1540684 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.7583. Min Act: -0.0000

Data Index: 1454323 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 6.0739. Min Range: -6.0739

Max Act: 3.8441. Min Act: -0.0000

Data Index: 1601383 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.3234. Min Act: -0.0000

Data Index: 1397039 (Python Code)

Max Activating Token Index: 780

Text #18

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.3153. Min Act: -0.0000

Data Index: 1477261 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 6.0739. Min Range: -6.0739

Max Act: 4.1086. Min Act: -0.0000

Data Index: 1492806 (Python Code)

Max Activating Token Index: 90