Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 781 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0000

Data Index: 422964 (The Pile)

Max Activating Token Index: 205

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5811. Min Act: -0.0000

Data Index: 948576 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5208. Min Act: -0.0000

Data Index: 13531 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1286209 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4488. Min Act: -0.0000

Data Index: 970833 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1627216 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4474. Min Act: -0.0000

Data Index: 627815 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1132314 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1798281 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4352. Min Act: -0.0000

Data Index: 995831 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4106. Min Act: -0.0000

Data Index: 133940 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1414666 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1700817 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1713159 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1376042 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3931. Min Act: -0.0000

Data Index: 423849 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1669447 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1770868 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1015272 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3943. Min Act: -0.0000

Data Index: 120056 (The Pile)

Max Activating Token Index: 937