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

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

Neuron 3771 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1845. Min Range: -1.1845

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1656967 (Python Code)

Max Activating Token Index: 378

Text #1

Max Range: 1.1845. Min Range: -1.1845

Max Act: 1.1845. Min Act: -0.0000

Data Index: 157470 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.1845. Min Range: -1.1845

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1390855 (Python Code)

Max Activating Token Index: 849

Text #3

Max Range: 1.1845. Min Range: -1.1845

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1634408 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.9973. Min Act: -0.0000

Data Index: 529456 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.9956. Min Act: -0.0000

Data Index: 381288 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1408014 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1351283 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.8020. Min Act: -0.0000

Data Index: 47777 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1124226 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.8496. Min Act: -0.0000

Data Index: 959158 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1237380 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1355583 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1495181 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.7864. Min Act: -0.0000

Data Index: 833030 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.7993. Min Act: -0.0000

Data Index: 62174 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1617315 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1655837 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1113496 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 1.1845. Min Range: -1.1845

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1642107 (Python Code)

Max Activating Token Index: 81