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

Dataset: The Pile

Neuron 3219 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1482631 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7226. Min Act: -0.0000

Data Index: 568441 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6773. Min Act: -0.0000

Data Index: 1882461 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1962938 (The Pile)

Max Activating Token Index: 530

Text #4

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1518163 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1386363 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5514. Min Act: -0.0000

Data Index: 1726757 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.4073. Min Act: -0.0000

Data Index: 1668161 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.3945. Min Act: -0.0000

Data Index: 1423554 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.4893. Min Act: -0.0000

Data Index: 212189 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1685991 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1338210 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.4019. Min Act: -0.0000

Data Index: 603544 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.3931. Min Act: -0.0000

Data Index: 77685 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5777. Min Act: -0.0000

Data Index: 1279417 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1048391 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1547945 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1374007 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1963476 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.2101. Min Act: -0.0000

Data Index: 496104 (The Pile)

Max Activating Token Index: 427