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

Dataset: The Pile

Neuron 3603 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: 5.0242. Min Range: -5.0242

Max Act: 5.0242. Min Act: -0.0000

Data Index: 1903851 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.0287. Min Act: -0.0000

Data Index: 1792149 (The Pile)

Max Activating Token Index: 1005

Text #2

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9114. Min Act: -0.0000

Data Index: 1166224 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.0289. Min Act: -0.0000

Data Index: 1295096 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.0143. Min Act: -0.0000

Data Index: 235703 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.5980. Min Act: -0.0000

Data Index: 461118 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.5192. Min Act: -0.0000

Data Index: 10722 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.8170. Min Act: -0.0000

Data Index: 825623 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.2916. Min Act: -0.0000

Data Index: 462519 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.1391. Min Act: -0.0000

Data Index: 1924972 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.1975. Min Act: -0.0000

Data Index: 532972 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.0833. Min Act: -0.0000

Data Index: 312212 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.0212. Min Act: -0.0000

Data Index: 672389 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 5.0242. Min Range: -5.0242

Max Act: 2.8491. Min Act: -0.0000

Data Index: 1462144 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.0848. Min Act: -0.0000

Data Index: 832487 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.0819. Min Act: -0.0000

Data Index: 1021851 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 5.0242. Min Range: -5.0242

Max Act: 2.9194. Min Act: -0.0000

Data Index: 179698 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 5.0242. Min Range: -5.0242

Max Act: 2.7552. Min Act: -0.0000

Data Index: 1042214 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 5.0242. Min Range: -5.0242

Max Act: 2.8864. Min Act: -0.0000

Data Index: 1649440 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 5.0242. Min Range: -5.0242

Max Act: 2.8333. Min Act: -0.0000

Data Index: 339226 (The Pile)

Max Activating Token Index: 462