Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 929 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.1310. Min Act: -0.0001

Data Index: 447637 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9889. Min Act: -0.0001

Data Index: 415144 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8861. Min Act: -0.0001

Data Index: 806514 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9479. Min Act: -0.0001

Data Index: 159089 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9775. Min Act: -0.0001

Data Index: 778431 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9717. Min Act: -0.0001

Data Index: 459030 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0408. Min Act: -0.0001

Data Index: 417967 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8557. Min Act: -0.0001

Data Index: 755325 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8549. Min Act: -0.0001

Data Index: 1265557 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8599. Min Act: -0.0001

Data Index: 1027234 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1086209 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1282768 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8729. Min Act: -0.0001

Data Index: 1084280 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8484. Min Act: -0.0001

Data Index: 529572 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1034468 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.7955. Min Act: -0.0001

Data Index: 14160 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8695. Min Act: -0.0001

Data Index: 621057 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1463626 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8562. Min Act: -0.0001

Data Index: 657235 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8330. Min Act: -0.0001

Data Index: 864944 (C4 (Web Text))

Max Activating Token Index: 766