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

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

Neuron 3656 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0450. Min Range: -1.0450

Max Act: 1.0450. Min Act: -0.0000

Data Index: 848747 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9796. Min Act: -0.0000

Data Index: 278811 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1155842 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9100. Min Act: -0.0000

Data Index: 724356 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9638. Min Act: -0.0000

Data Index: 386480 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9456. Min Act: -0.0000

Data Index: 339600 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9420. Min Act: -0.0000

Data Index: 724871 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8361. Min Act: -0.0000

Data Index: 412128 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8939. Min Act: -0.0000

Data Index: 516874 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8585. Min Act: -0.0000

Data Index: 694264 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1014150 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8680. Min Act: -0.0000

Data Index: 739369 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9078. Min Act: -0.0000

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.9068. Min Act: -0.0000

Data Index: 854473 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 1.0450. Min Range: -1.0450

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1173124 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1094226 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1091713 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1190088 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8424. Min Act: -0.0000

Data Index: 79114 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.0450. Min Range: -1.0450

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1147982 (C4 (Web Text))

Max Activating Token Index: 431