Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 810 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6860. Min Act: -0.0001

Data Index: 1532302 (Python Code)

Max Activating Token Index: 730

Text #1

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1386665 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4529. Min Act: -0.0001

Data Index: 1559056 (Python Code)

Max Activating Token Index: 478

Text #3

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4256. Min Act: -0.0001

Data Index: 1584821 (Python Code)

Max Activating Token Index: 309

Text #4

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4679. Min Act: -0.0001

Data Index: 1391979 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1364233 (Python Code)

Max Activating Token Index: 938

Text #6

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1401595 (Python Code)

Max Activating Token Index: 879

Text #7

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1600721 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3390. Min Act: -0.0001

Data Index: 1653038 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3403. Min Act: -0.0001

Data Index: 1528098 (Python Code)

Max Activating Token Index: 637

Text #10

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3563. Min Act: -0.0001

Data Index: 1519719 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3402. Min Act: -0.0001

Data Index: 1492141 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1629403 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3220. Min Act: -0.0001

Data Index: 1605771 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1405973 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1527122 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1402346 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1620101 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.2747. Min Act: -0.0001

Data Index: 1426760 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.2641. Min Act: -0.0001

Data Index: 1633186 (Python Code)

Max Activating Token Index: 370