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

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

Neuron 5916 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.8687. Min Act: -0.0000

Data Index: 663843 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.7805. Min Act: -0.0000

Data Index: 187106 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.7517. Min Act: -0.0000

Data Index: 876500 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.4023. Min Act: -0.0000

Data Index: 1300918 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.4733. Min Act: -0.0000

Data Index: 1037616 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.6167. Min Act: -0.0000

Data Index: 728242 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.2664. Min Act: -0.0000

Data Index: 670303 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.3064. Min Act: -0.0000

Data Index: 445262 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.3760. Min Act: -0.0000

Data Index: 501994 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.2674. Min Act: -0.0000

Data Index: 27588 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.2227. Min Act: -0.0000

Data Index: 99067 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.2211. Min Act: -0.0000

Data Index: 338551 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1200720 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.0580. Min Act: -0.0000

Data Index: 947698 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.1943. Min Act: -0.0000

Data Index: 1155621 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.1358. Min Act: -0.0000

Data Index: 1180676 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.1538. Min Act: -0.0000

Data Index: 998485 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.2318. Min Act: -0.0000

Data Index: 487699 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.0103. Min Act: -0.0000

Data Index: 1068853 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 2.8687. Min Range: -2.8687

Max Act: 2.0049. Min Act: -0.0000

Data Index: 342072 (C4 (Web Text))

Max Activating Token Index: 401