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

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

Neuron 1349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2591. Min Act: -0.0000

Data Index: 617781 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2466. Min Act: -0.0000

Data Index: 763734 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2288. Min Act: -0.0001

Data Index: 882538 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2095. Min Act: -0.0000

Data Index: 725601 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2287. Min Act: -0.0001

Data Index: 369006 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2023. Min Act: -0.0001

Data Index: 242728 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2089. Min Act: -0.0001

Data Index: 371151 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1198620 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1918. Min Act: -0.0001

Data Index: 522108 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1127689 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1890. Min Act: -0.0001

Data Index: 750336 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1901. Min Act: -0.0001

Data Index: 276754 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1874. Min Act: -0.0001

Data Index: 76848 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1903. Min Act: -0.0000

Data Index: 833647 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1311269 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1803. Min Act: -0.0001

Data Index: 635368 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1695. Min Act: -0.0000

Data Index: 333216 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1153400 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1952. Min Act: -0.0001

Data Index: 992159 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1786. Min Act: -0.0000

Data Index: 264075 (C4 (Web Text))

Max Activating Token Index: 829