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

Dataset: The Pile

Neuron 2050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1296521 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7829. Min Act: -0.0000

Data Index: 895362 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7474. Min Act: -0.0000

Data Index: 601057 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7559. Min Act: -0.0000

Data Index: 950885 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7614. Min Act: -0.0000

Data Index: 183221 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1558426 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7267. Min Act: -0.0000

Data Index: 429327 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7434. Min Act: -0.0000

Data Index: 952 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7600. Min Act: -0.0000

Data Index: 905927 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1039688 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1110073 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1682638 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1587282 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6753. Min Act: -0.0000

Data Index: 203605 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1712716 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1025781 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6663. Min Act: -0.0001

Data Index: 198433 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5934. Min Act: -0.0001

Data Index: 26292 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1984300 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1025951 (The Pile)

Max Activating Token Index: 703