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

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

Neuron 75 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: 1.5248. Min Range: -1.5248

Max Act: 1.5248. Min Act: -0.0001

Data Index: 1554401 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 1.5248. Min Range: -1.5248

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1534038 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 1.5248. Min Range: -1.5248

Max Act: 1.0622. Min Act: -0.0001

Data Index: 1648886 (Python Code)

Max Activating Token Index: 249

Text #3

Max Range: 1.5248. Min Range: -1.5248

Max Act: 1.1205. Min Act: -0.0001

Data Index: 1374300 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.9546. Min Act: -0.0001

Data Index: 1463599 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8796. Min Act: -0.0001

Data Index: 1630040 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.9652. Min Act: -0.0001

Data Index: 1614009 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8771. Min Act: -0.0001

Data Index: 1589271 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1598456 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8555. Min Act: -0.0001

Data Index: 1449992 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1433889 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.9193. Min Act: -0.0001

Data Index: 1572074 (Python Code)

Max Activating Token Index: 820

Text #12

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1418669 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8010. Min Act: -0.0001

Data Index: 1617134 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8092. Min Act: -0.0001

Data Index: 129691 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8236. Min Act: -0.0001

Data Index: 1372769 (Python Code)

Max Activating Token Index: 1001

Text #16

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8422. Min Act: -0.0001

Data Index: 1431102 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.8356. Min Act: -0.0001

Data Index: 1592205 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1636729 (Python Code)

Max Activating Token Index: 171

Text #19

Max Range: 1.5248. Min Range: -1.5248

Max Act: 0.7670. Min Act: -0.0001

Data Index: 1417970 (Python Code)

Max Activating Token Index: 390