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

Dataset: The Pile

Neuron 1184 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1115587 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.9112. Min Act: -0.0000

Data Index: 13275 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.8765. Min Act: -0.0000

Data Index: 179905 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1890943 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1226153 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6643. Min Act: -0.0000

Data Index: 55824 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7213. Min Act: -0.0000

Data Index: 923976 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6838. Min Act: -0.0000

Data Index: 297346 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1514169 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1526944 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1844486 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1354413 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1075045 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6719. Min Act: -0.0000

Data Index: 502052 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6950. Min Act: -0.0000

Data Index: 555890 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1422646 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6229. Min Act: -0.0000

Data Index: 915848 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1866123 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1982183 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1327741 (The Pile)

Max Activating Token Index: 972