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

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

Neuron 705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.6536. Min Act: -0.0001

Data Index: 126297 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.6648. Min Act: -0.0001

Data Index: 720778 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5636. Min Act: -0.0001

Data Index: 553455 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5965. Min Act: -0.0001

Data Index: 1229169 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.4147. Min Act: -0.0001

Data Index: 915657 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5313. Min Act: -0.0001

Data Index: 161334 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.4996. Min Act: -0.0001

Data Index: 323743 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5406. Min Act: -0.0001

Data Index: 823880 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5485. Min Act: -0.0001

Data Index: 98776 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.3426. Min Act: -0.0001

Data Index: 455685 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5191. Min Act: -0.0001

Data Index: 825837 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.4883. Min Act: -0.0001

Data Index: 94951 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.3172. Min Act: -0.0001

Data Index: 1194127 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.2128. Min Act: -0.0001

Data Index: 56540 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.3185. Min Act: -0.0001

Data Index: 784749 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.3518. Min Act: -0.0001

Data Index: 723375 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.5370. Min Act: -0.0001

Data Index: 1030522 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.3701. Min Act: -0.0001

Data Index: 1002589 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.3344. Min Act: -0.0001

Data Index: 1358042 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.2636. Min Act: -0.0001

Data Index: 427 (C4 (Web Text))

Max Activating Token Index: 569