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

Dataset: The Pile

Neuron 4492 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1243227 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0120. Min Act: -0.0000

Data Index: 988795 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1737933 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1365129 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0240. Min Act: -0.0000

Data Index: 5752 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1682317 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0212. Min Act: -0.0000

Data Index: 453248 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1408823 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8259. Min Act: 0.0000

Data Index: 1849776 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0334. Min Act: 0.0001

Data Index: 1493868 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1690769 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1127101 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1806417 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.7879. Min Act: -0.0000

Data Index: 924329 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 1.2947. Min Range: -1.2947

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1357929 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1690137 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8277. Min Act: -0.0000

Data Index: 908715 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1732588 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1512655 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 1.2947. Min Range: -1.2947

Max Act: 0.8837. Min Act: -0.0000

Data Index: 143840 (The Pile)

Max Activating Token Index: 252