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

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

Neuron 3792 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: 1.8102. Min Range: -1.8102

Max Act: 1.8102. Min Act: -0.0001

Data Index: 508472 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.3735. Min Act: -0.0000

Data Index: 749193 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.4462. Min Act: -0.0000

Data Index: 435272 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.3934. Min Act: -0.0000

Data Index: 813475 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.3826. Min Act: -0.0001

Data Index: 1146303 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1072499 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.2725. Min Act: -0.0001

Data Index: 1138613 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.0702. Min Act: -0.0001

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.3291. Min Act: -0.0001

Data Index: 282244 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.0983. Min Act: -0.0001

Data Index: 365686 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.1611. Min Act: -0.0001

Data Index: 308976 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.2592. Min Act: -0.0001

Data Index: 1249793 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.0742. Min Act: -0.0000

Data Index: 518353 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.2436. Min Act: -0.0000

Data Index: 907054 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.2069. Min Act: -0.0000

Data Index: 451337 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.0675. Min Act: -0.0001

Data Index: 253758 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 1.8102. Min Range: -1.8102

Max Act: 0.9916. Min Act: -0.0000

Data Index: 891443 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1109039 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.2248. Min Act: -0.0000

Data Index: 238673 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.1185. Min Act: -0.0000

Data Index: 716483 (C4 (Web Text))

Max Activating Token Index: 569