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

Dataset: The Pile

Neuron 2005 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: 3.6121. Min Range: -3.6121

Max Act: 3.5479. Min Act: -0.0000

Data Index: 110682 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.1350. Min Act: -0.0000

Data Index: 1249123 (The Pile)

Max Activating Token Index: 861

Text #2

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.9972. Min Act: -0.0000

Data Index: 1886714 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.2967. Min Act: -0.0000

Data Index: 230439 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.6121. Min Act: -0.0000

Data Index: 1190248 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.0361. Min Act: -0.0000

Data Index: 1850320 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.3724. Min Act: -0.0000

Data Index: 1717187 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.3748. Min Act: -0.0000

Data Index: 633575 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.6004. Min Act: -0.0000

Data Index: 303247 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.9293. Min Act: -0.0000

Data Index: 1342 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.8916. Min Act: -0.0000

Data Index: 1804925 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.1197. Min Act: -0.0000

Data Index: 1735848 (The Pile)

Max Activating Token Index: 683

Text #12

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.0685. Min Act: -0.0000

Data Index: 1990425 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.0822. Min Act: -0.0000

Data Index: 319337 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.9944. Min Act: -0.0000

Data Index: 1156442 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.0842. Min Act: -0.0000

Data Index: 986003 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.5968. Min Act: -0.0000

Data Index: 399902 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 3.6121. Min Range: -3.6121

Max Act: 2.7768. Min Act: -0.0000

Data Index: 1624914 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.0501. Min Act: -0.0000

Data Index: 1210484 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 3.6121. Min Range: -3.6121

Max Act: 3.0123. Min Act: -0.0000

Data Index: 1220130 (The Pile)

Max Activating Token Index: 408