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

Dataset: The Pile

Neuron 404 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1848301 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1717254 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1148440 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1379652 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5073. Min Act: -0.0000

Data Index: 614563 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1452272 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1658809 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1084306 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5613. Min Act: -0.0000

Data Index: 698662 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5257. Min Act: -0.0000

Data Index: 275319 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1173340 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5042. Min Act: -0.0000

Data Index: 79453 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4861. Min Act: -0.0000

Data Index: 464220 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5387. Min Act: 0.0000

Data Index: 1964758 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1325969 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.5306. Min Act: -0.0000

Data Index: 248201 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4450. Min Act: -0.0000

Data Index: 488086 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1078527 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1141865 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.6441. Min Range: -0.6441

Max Act: 0.4658. Min Act: -0.0000

Data Index: 846950 (The Pile)

Max Activating Token Index: 386