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

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

Neuron 335 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.6784. Min Act: -0.0000

Data Index: 189050 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3980. Min Act: -0.0000

Data Index: 761101 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3419. Min Act: -0.0000

Data Index: 587134 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1827. Min Act: -0.0000

Data Index: 780505 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3860. Min Act: -0.0000

Data Index: 597099 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3602. Min Act: -0.0000

Data Index: 300237 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3818. Min Act: -0.0000

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3637. Min Act: -0.0000

Data Index: 653636 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2333. Min Act: -0.0000

Data Index: 1180996 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3285. Min Act: -0.0000

Data Index: 457917 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3145. Min Act: -0.0000

Data Index: 997316 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3283. Min Act: -0.0000

Data Index: 977670 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2806. Min Act: -0.0000

Data Index: 1118756 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1145. Min Act: -0.0000

Data Index: 1095521 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1334. Min Act: -0.0000

Data Index: 53255 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1432. Min Act: -0.0000

Data Index: 98437 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2564. Min Act: -0.0000

Data Index: 432800 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.1191. Min Act: -0.0000

Data Index: 640025 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.2020. Min Act: -0.0000

Data Index: 100806 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.6784. Min Range: -2.6784

Max Act: 2.3274. Min Act: -0.0000

Data Index: 1077783 (C4 (Web Text))

Max Activating Token Index: 155