Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0894. Min Range: -3.0894

Max Act: 3.0894. Min Act: -0.0000

Data Index: 351618 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.6023. Min Act: -0.0000

Data Index: 71874 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.6587. Min Act: -0.0000

Data Index: 1185234 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.4544. Min Act: -0.0000

Data Index: 1167779 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.5616. Min Act: -0.0000

Data Index: 562017 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.3748. Min Act: -0.0000

Data Index: 800380 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.1599. Min Act: -0.0000

Data Index: 878804 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1283401 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.2121. Min Act: -0.0000

Data Index: 307817 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.3060. Min Act: -0.0000

Data Index: 285523 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.3112. Min Act: -0.0000

Data Index: 1222668 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9435. Min Act: -0.0000

Data Index: 1183739 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.0342. Min Act: -0.0000

Data Index: 1166797 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 3.0894. Min Range: -3.0894

Max Act: 2.1065. Min Act: -0.0000

Data Index: 1243540 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9647. Min Act: -0.0000

Data Index: 375681 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9541. Min Act: -0.0000

Data Index: 594082 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9380. Min Act: -0.0000

Data Index: 681104 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9322. Min Act: -0.0000

Data Index: 855555 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9130. Min Act: -0.0000

Data Index: 1237164 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 3.0894. Min Range: -3.0894

Max Act: 1.9153. Min Act: -0.0000

Data Index: 822988 (C4 (Web Text))

Max Activating Token Index: 423