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

Dataset: The Pile

Neuron 4323 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: 0.5322. Min Range: -0.5322

Max Act: 0.5322. Min Act: -0.0000

Data Index: 839547 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4745. Min Act: -0.0000

Data Index: 729100 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1911417 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4407. Min Act: -0.0000

Data Index: 962912 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4506. Min Act: -0.0000

Data Index: 252119 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1924757 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1372270 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5011. Min Act: -0.0000

Data Index: 559284 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1002710 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1481957 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1967195 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1052886 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4731. Min Act: -0.0000

Data Index: 921186 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4703. Min Act: -0.0000

Data Index: 715545 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4628. Min Act: -0.0000

Data Index: 44603 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4931. Min Act: -0.0000

Data Index: 96039 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1810307 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4382. Min Act: -0.0000

Data Index: 606044 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4470. Min Act: -0.0000

Data Index: 539619 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4567. Min Act: -0.0000

Data Index: 621969 (The Pile)

Max Activating Token Index: 182