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

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

Neuron 1563 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1557587 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1631027 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1644373 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1524370 (Python Code)

Max Activating Token Index: 568

Text #4

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1431322 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1538457 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1488011 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1462625 (Python Code)

Max Activating Token Index: 752

Text #8

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1574141 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1441293 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1367693 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1585960 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1427458 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2526. Min Act: -0.0000

Data Index: 432876 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1656092 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1429046 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1486701 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1617534 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1641834 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1457656 (Python Code)

Max Activating Token Index: 93