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

Dataset: The Pile

Neuron 1073 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: 4.4339. Min Range: -4.4339

Max Act: 4.4339. Min Act: -0.0000

Data Index: 535782 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.3428. Min Act: -0.0000

Data Index: 653403 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.6810. Min Act: -0.0000

Data Index: 414937 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.7681. Min Act: -0.0000

Data Index: 1035480 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.4791. Min Act: -0.0000

Data Index: 486881 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.3091. Min Act: -0.0000

Data Index: 1290454 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.1607. Min Act: -0.0000

Data Index: 1246947 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.0771. Min Act: -0.0000

Data Index: 1136295 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.0306. Min Act: -0.0000

Data Index: 762738 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.1157. Min Act: -0.0000

Data Index: 430157 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 4.4339. Min Range: -4.4339

Max Act: 2.7658. Min Act: -0.0000

Data Index: 103687 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.3315. Min Act: -0.0000

Data Index: 1057633 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 4.4339. Min Range: -4.4339

Max Act: 2.9362. Min Act: -0.0000

Data Index: 1007261 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.3849. Min Act: -0.0000

Data Index: 1063182 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 4.4339. Min Range: -4.4339

Max Act: 2.7923. Min Act: -0.0000

Data Index: 1232802 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.0818. Min Act: -0.0000

Data Index: 1084757 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.0179. Min Act: -0.0000

Data Index: 432715 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 4.4339. Min Range: -4.4339

Max Act: 2.9123. Min Act: -0.0000

Data Index: 1346547 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 4.4339. Min Range: -4.4339

Max Act: 3.0167. Min Act: -0.0000

Data Index: 1004906 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 4.4339. Min Range: -4.4339

Max Act: 2.9839. Min Act: -0.0000

Data Index: 126025 (The Pile)

Max Activating Token Index: 295