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

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

Neuron 162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7669. Min Act: -0.0002

Data Index: 800792 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8457. Min Act: -0.0002

Data Index: 889738 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7594. Min Act: -0.0002

Data Index: 550729 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7011. Min Act: -0.0002

Data Index: 1084020 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7627. Min Act: -0.0002

Data Index: 1263208 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6748. Min Act: -0.0002

Data Index: 557723 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6907. Min Act: -0.0002

Data Index: 1187474 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6573. Min Act: -0.0002

Data Index: 1344173 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6403. Min Act: -0.0002

Data Index: 158581 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6411. Min Act: -0.0002

Data Index: 1312972 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6118. Min Act: -0.0002

Data Index: 829363 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6138. Min Act: -0.0002

Data Index: 1284272 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6712. Min Act: -0.0002

Data Index: 771128 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6691. Min Act: -0.0002

Data Index: 841049 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5683. Min Act: -0.0002

Data Index: 138004 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6935. Min Act: -0.0002

Data Index: 495932 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5891. Min Act: -0.0002

Data Index: 773021 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6638. Min Act: -0.0002

Data Index: 417433 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5973. Min Act: -0.0002

Data Index: 916431 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6206. Min Act: -0.0002

Data Index: 1280572 (C4 (Web Text))

Max Activating Token Index: 139