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

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

Neuron 5632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.7098. Min Act: -0.0000

Data Index: 1243108 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.5616. Min Act: -0.0001

Data Index: 145479 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.8151. Min Act: -0.0000

Data Index: 808819 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 9.2538. Min Range: -9.2538

Max Act: 9.2538. Min Act: -0.0000

Data Index: 1173356 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.7863. Min Act: -0.0000

Data Index: 247006 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.7911. Min Act: -0.0000

Data Index: 1309754 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 9.2538. Min Range: -9.2538

Max Act: 9.0815. Min Act: -0.0000

Data Index: 231398 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.3690. Min Act: -0.0000

Data Index: 438515 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 9.2538. Min Range: -9.2538

Max Act: 7.7600. Min Act: -0.0000

Data Index: 847893 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.5365. Min Act: -0.0000

Data Index: 642102 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.8113. Min Act: -0.0000

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.1278. Min Act: -0.0000

Data Index: 1104146 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.2909. Min Act: -0.0000

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.2246. Min Act: -0.0000

Data Index: 573258 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.4231. Min Act: -0.0000

Data Index: 715071 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.7785. Min Act: -0.0000

Data Index: 1236031 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.0487. Min Act: -0.0000

Data Index: 338240 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.1603. Min Act: -0.0000

Data Index: 162810 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 9.2538. Min Range: -9.2538

Max Act: 7.9912. Min Act: -0.0000

Data Index: 317619 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 9.2538. Min Range: -9.2538

Max Act: 8.3647. Min Act: -0.0000

Data Index: 634750 (C4 (Web Text))

Max Activating Token Index: 443