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

Dataset: The Pile

Neuron 5013 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: 3.6406. Min Range: -3.6406

Max Act: 3.1814. Min Act: -0.0000

Data Index: 1114478 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.6406. Min Act: -0.0000

Data Index: 573141 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.4396. Min Act: -0.0000

Data Index: 1169002 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.2795. Min Act: -0.0000

Data Index: 1160946 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.2768. Min Act: -0.0000

Data Index: 1118622 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.2327. Min Act: -0.0000

Data Index: 856569 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.1974. Min Act: -0.0000

Data Index: 432230 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0285. Min Act: -0.0000

Data Index: 1762000 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.7393. Min Act: -0.0000

Data Index: 124394 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.8697. Min Act: -0.0000

Data Index: 1942452 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.7836. Min Act: -0.0000

Data Index: 389436 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.2019. Min Act: -0.0000

Data Index: 1958206 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.9024. Min Act: -0.0000

Data Index: 310536 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.8871. Min Act: -0.0000

Data Index: 1339641 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0167. Min Act: -0.0000

Data Index: 1414298 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.7673. Min Act: -0.0000

Data Index: 1305099 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0020. Min Act: -0.0000

Data Index: 54157 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.8446. Min Act: -0.0000

Data Index: 678976 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 3.6406. Min Range: -3.6406

Max Act: 3.0002. Min Act: -0.0000

Data Index: 793760 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 3.6406. Min Range: -3.6406

Max Act: 2.9853. Min Act: -0.0000

Data Index: 125686 (The Pile)

Max Activating Token Index: 409