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

Dataset: The Pile

Neuron 2586 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1471. Min Act: -0.0000

Data Index: 805601 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0949. Min Act: -0.0000

Data Index: 46669 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0942. Min Act: -0.0000

Data Index: 314569 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.8551. Min Act: -0.0000

Data Index: 411268 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.7182. Min Act: -0.0000

Data Index: 615212 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.8366. Min Act: -0.0000

Data Index: 1789302 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.8020. Min Act: -0.0000

Data Index: 1409501 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.7937. Min Act: -0.0000

Data Index: 1603190 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.7709. Min Act: -0.0000

Data Index: 1703922 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.6310. Min Act: -0.0000

Data Index: 271711 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.6596. Min Act: -0.0000

Data Index: 1929271 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.5878. Min Act: -0.0000

Data Index: 1022894 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.6920. Min Act: -0.0000

Data Index: 1431718 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.5012. Min Act: -0.0000

Data Index: 1781100 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.7449. Min Act: -0.0000

Data Index: 1742390 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.6188. Min Act: -0.0000

Data Index: 1522220 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.4532. Min Act: -0.0000

Data Index: 1025337 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.5929. Min Act: -0.0000

Data Index: 613390 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.5904. Min Act: -0.0000

Data Index: 1788608 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 3.1471. Min Range: -3.1471

Max Act: 2.5616. Min Act: -0.0000

Data Index: 1944478 (The Pile)

Max Activating Token Index: 394