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

Dataset: The Pile

Neuron 169 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.6974. Min Act: -0.0000

Data Index: 877053 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1904160 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1236678 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.6642. Min Act: -0.0000

Data Index: 861805 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.7040. Min Act: -0.0000

Data Index: 385332 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.6411. Min Act: -0.0000

Data Index: 549273 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1281411 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5078. Min Act: -0.0000

Data Index: 693427 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5892. Min Act: -0.0000

Data Index: 297550 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5808. Min Act: -0.0000

Data Index: 47854 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5966. Min Act: -0.0000

Data Index: 556449 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1115635 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1344597 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5671. Min Act: -0.0000

Data Index: 143035 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5407. Min Act: -0.0000

Data Index: 560920 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5772. Min Act: -0.0000

Data Index: 629666 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1956139 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5260. Min Act: -0.0000

Data Index: 91310 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1991688 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.7727. Min Range: -0.7727

Max Act: 0.5083. Min Act: -0.0000

Data Index: 692990 (The Pile)

Max Activating Token Index: 942