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

Dataset: The Pile

Neuron 86 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: 1.6332. Min Range: -1.6332

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1242769 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.3281. Min Act: -0.0000

Data Index: 349632 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1894. Min Act: -0.0000

Data Index: 633143 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1729. Min Act: -0.0000

Data Index: 848227 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1310. Min Act: -0.0000

Data Index: 644464 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1925682 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1795628 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0508. Min Act: -0.0000

Data Index: 230871 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1883000 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1640866 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1629. Min Act: -0.0000

Data Index: 686174 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.9997. Min Act: -0.0000

Data Index: 908133 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0815. Min Act: -0.0000

Data Index: 191811 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1857775 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.9783. Min Act: -0.0000

Data Index: 373915 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1583321 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1424. Min Act: -0.0000

Data Index: 948025 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1632017 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0938. Min Act: -0.0000

Data Index: 100535 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0489. Min Act: -0.0000

Data Index: 205922 (The Pile)

Max Activating Token Index: 149