Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3031 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0001

Data Index: 123291 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2437. Min Act: -0.0001

Data Index: 41753 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2201. Min Act: -0.0001

Data Index: 223653 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2379. Min Act: -0.0001

Data Index: 213001 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2115. Min Act: -0.0001

Data Index: 508260 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2009. Min Act: -0.0001

Data Index: 546337 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1953. Min Act: -0.0001

Data Index: 782749 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1906. Min Act: -0.0001

Data Index: 423262 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2023. Min Act: -0.0001

Data Index: 671866 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2026. Min Act: -0.0001

Data Index: 377326 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1181338 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1958. Min Act: -0.0001

Data Index: 506304 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1058599 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1771. Min Act: -0.0001

Data Index: 583954 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1277246 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1815. Min Act: -0.0001

Data Index: 429159 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1865. Min Act: -0.0001

Data Index: 471589 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1731. Min Act: -0.0001

Data Index: 63421 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1045688 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1711. Min Act: -0.0001

Data Index: 56667 (C4 (Web Text))

Max Activating Token Index: 476