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

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

Neuron 5585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.6675. Min Act: -0.0000

Data Index: 239318 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.6362. Min Act: -0.0000

Data Index: 915026 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.8032. Min Act: -0.0000

Data Index: 843121 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.6177. Min Act: -0.0000

Data Index: 611209 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5893. Min Act: -0.0000

Data Index: 1171024 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5700. Min Act: -0.0000

Data Index: 727456 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7567. Min Act: -0.0000

Data Index: 350589 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7416. Min Act: -0.0000

Data Index: 348599 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5120. Min Act: -0.0000

Data Index: 808459 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.6360. Min Act: -0.0000

Data Index: 718484 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.2354. Min Act: -0.0000

Data Index: 1141333 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7922. Min Act: -0.0000

Data Index: 353911 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.4177. Min Act: -0.0000

Data Index: 203365 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7908. Min Act: -0.0000

Data Index: 567397 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.3941. Min Act: -0.0000

Data Index: 204097 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5763. Min Act: -0.0000

Data Index: 946185 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5565. Min Act: -0.0000

Data Index: 558003 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5799. Min Act: -0.0000

Data Index: 738025 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.5598. Min Act: -0.0000

Data Index: 1317084 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 4.8032. Min Range: -4.8032

Max Act: 4.7462. Min Act: -0.0000

Data Index: 1081163 (C4 (Web Text))

Max Activating Token Index: 547