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

Dataset: The Pile

Neuron 3169 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0402. Min Range: -5.0402

Max Act: 5.0402. Min Act: -0.0000

Data Index: 942679 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1350. Min Act: -0.0000

Data Index: 264235 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.6678. Min Act: -0.0000

Data Index: 1764795 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1280. Min Act: -0.0000

Data Index: 284322 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1020. Min Act: -0.0000

Data Index: 837077 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.8179. Min Act: -0.0000

Data Index: 282793 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.9948. Min Act: -0.0000

Data Index: 813605 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.1009. Min Act: -0.0000

Data Index: 1849623 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.9499. Min Act: -0.0000

Data Index: 1153801 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 5.0402. Min Range: -5.0402

Max Act: 4.4213. Min Act: -0.0000

Data Index: 1555179 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.7277. Min Act: -0.0000

Data Index: 885904 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.5342. Min Act: -0.0000

Data Index: 840609 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.7791. Min Act: -0.0000

Data Index: 1640 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.5215. Min Act: -0.0000

Data Index: 1015522 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.1780. Min Act: -0.0000

Data Index: 212728 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.4403. Min Act: -0.0000

Data Index: 453837 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.9358. Min Act: -0.0000

Data Index: 1953039 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.5717. Min Act: -0.0000

Data Index: 1410862 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.5982. Min Act: -0.0000

Data Index: 988629 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 5.0402. Min Range: -5.0402

Max Act: 3.6903. Min Act: -0.0000

Data Index: 88265 (The Pile)

Max Activating Token Index: 888