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

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

Neuron 196 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: 0.3576. Min Range: -0.3576

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1462429 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1373604 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1649452 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1440202 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1631134 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1457145 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1429739 (Python Code)

Max Activating Token Index: 578

Text #7

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1572469 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1387802 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1422515 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1646430 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1565804 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1500057 (Python Code)

Max Activating Token Index: 402

Text #13

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1584106 (Python Code)

Max Activating Token Index: 812

Text #14

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1607011 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1632321 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1542656 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1533401 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1529579 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.3576. Min Range: -0.3576

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1412207 (Python Code)

Max Activating Token Index: 653