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

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

Neuron 3842 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.9511. Min Act: -0.0001

Data Index: 687653 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.6599. Min Act: -0.0001

Data Index: 513040 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.6056. Min Act: -0.0001

Data Index: 488612 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.7172. Min Act: -0.0000

Data Index: 384309 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.7148. Min Act: -0.0001

Data Index: 566230 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.5873. Min Act: -0.0001

Data Index: 98418 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4129. Min Act: -0.0001

Data Index: 973919 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.5280. Min Act: -0.0000

Data Index: 173243 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4969. Min Act: -0.0001

Data Index: 200434 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1185972 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4829. Min Act: -0.0000

Data Index: 72789 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.5393. Min Act: -0.0001

Data Index: 1149735 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1070698 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4549. Min Act: -0.0001

Data Index: 867467 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.3790. Min Act: -0.0000

Data Index: 861147 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.6746. Min Act: -0.0000

Data Index: 559109 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4505. Min Act: -0.0001

Data Index: 12316 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4303. Min Act: -0.0000

Data Index: 584155 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.5638. Min Act: -0.0001

Data Index: 705152 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.9511. Min Range: -1.9511

Max Act: 1.4655. Min Act: -0.0000

Data Index: 47177 (C4 (Web Text))

Max Activating Token Index: 754