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

Dataset: The Pile

Neuron 300 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: 3.0303. Min Range: -3.0303

Max Act: 3.0303. Min Act: -0.0000

Data Index: 1722291 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.7638. Min Act: -0.0000

Data Index: 123378 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.6447. Min Act: -0.0000

Data Index: 1602257 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4934. Min Act: -0.0000

Data Index: 1274062 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.6224. Min Act: -0.0000

Data Index: 1703478 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.5775. Min Act: -0.0000

Data Index: 1458215 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.6310. Min Act: -0.0000

Data Index: 453784 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4865. Min Act: -0.0000

Data Index: 195665 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1602047 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4629. Min Act: -0.0000

Data Index: 868755 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4592. Min Act: -0.0000

Data Index: 1425547 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4759. Min Act: -0.0000

Data Index: 1832973 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4568. Min Act: -0.0000

Data Index: 1030484 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4450. Min Act: -0.0000

Data Index: 1488376 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4373. Min Act: -0.0000

Data Index: 215277 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4436. Min Act: -0.0000

Data Index: 1635525 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.4013. Min Act: -0.0000

Data Index: 1177402 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.3966. Min Act: -0.0000

Data Index: 288945 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.5180. Min Act: -0.0000

Data Index: 1201352 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.2652. Min Act: -0.0000

Data Index: 642852 (The Pile)

Max Activating Token Index: 512