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

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

Neuron 2007 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1059032 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.7305. Min Act: -0.0000

Data Index: 675858 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.6259. Min Act: 0.0000

Data Index: 1176879 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1202538 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5680. Min Act: 0.0000

Data Index: 213979 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5633. Min Act: 0.0000

Data Index: 1311180 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5489. Min Act: -0.0000

Data Index: 36316 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5451. Min Act: -0.0000

Data Index: 513603 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1088020 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4962. Min Act: -0.0000

Data Index: 788058 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4870. Min Act: 0.0001

Data Index: 976349 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4999. Min Act: -0.0000

Data Index: 931822 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1100057 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4772. Min Act: -0.0000

Data Index: 975877 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4445. Min Act: -0.0000

Data Index: 198141 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4328. Min Act: -0.0000

Data Index: 663972 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4384. Min Act: -0.0000

Data Index: 567035 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4547. Min Act: -0.0000

Data Index: 237791 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4612. Min Act: -0.0000

Data Index: 661163 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1181306 (C4 (Web Text))

Max Activating Token Index: 817