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

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

Neuron 926 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0000

Data Index: 705525 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1317864 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0756. Min Act: -0.0000

Data Index: 514949 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0753. Min Act: -0.0000

Data Index: 439475 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0682. Min Act: -0.0000

Data Index: 925212 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1144945 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0644. Min Act: -0.0000

Data Index: 819037 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1186567 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0673. Min Act: -0.0000

Data Index: 319133 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0620. Min Act: -0.0000

Data Index: 693951 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0614. Min Act: -0.0000

Data Index: 288781 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0608. Min Act: -0.0000

Data Index: 59186 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1067470 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0627. Min Act: -0.0000

Data Index: 989655 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0645. Min Act: -0.0000

Data Index: 290248 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0589. Min Act: -0.0000

Data Index: 22616 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1134526 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0610. Min Act: -0.0000

Data Index: 766091 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0605. Min Act: -0.0000

Data Index: 239638 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1071823 (C4 (Web Text))

Max Activating Token Index: 13