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

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

Neuron 2762 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: 4.5664. Min Range: -4.5664

Max Act: 4.5664. Min Act: -0.0000

Data Index: 394301 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 4.5664. Min Range: -4.5664

Max Act: 4.2971. Min Act: -0.0000

Data Index: 724502 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 4.5664. Min Range: -4.5664

Max Act: 4.2529. Min Act: -0.0000

Data Index: 75002 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.9795. Min Act: -0.0000

Data Index: 857017 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.9669. Min Act: -0.0000

Data Index: 737150 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.7535. Min Act: -0.0000

Data Index: 305907 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.5645. Min Act: -0.0000

Data Index: 16826 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.6995. Min Act: -0.0000

Data Index: 542081 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.8644. Min Act: -0.0000

Data Index: 628794 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.7421. Min Act: -0.0000

Data Index: 1139404 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.5932. Min Act: -0.0000

Data Index: 1161131 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.5434. Min Act: -0.0000

Data Index: 986566 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.4172. Min Act: -0.0000

Data Index: 889510 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.5565. Min Act: -0.0000

Data Index: 1251516 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.4812. Min Act: -0.0000

Data Index: 1113501 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.4370. Min Act: -0.0000

Data Index: 901205 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.2626. Min Act: -0.0000

Data Index: 773581 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.4134. Min Act: -0.0000

Data Index: 669291 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.3524. Min Act: -0.0000

Data Index: 1009330 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 4.5664. Min Range: -4.5664

Max Act: 3.3560. Min Act: -0.0000

Data Index: 132499 (C4 (Web Text))

Max Activating Token Index: 311