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

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

Neuron 1096 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: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0000

Data Index: 849235 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1056. Min Act: -0.0000

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1337596 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1088071 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1062. Min Act: -0.0001

Data Index: 298981 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1090233 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1218353 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0902. Min Act: -0.0001

Data Index: 389177 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0940. Min Act: -0.0001

Data Index: 979948 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0922. Min Act: -0.0000

Data Index: 104720 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0931. Min Act: -0.0001

Data Index: 465547 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0960. Min Act: -0.0001

Data Index: 271293 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1221325 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0876. Min Act: -0.0001

Data Index: 465651 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0839. Min Act: -0.0000

Data Index: 548127 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1182337 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0821. Min Act: -0.0000

Data Index: 205338 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0909. Min Act: -0.0001

Data Index: 274651 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0871. Min Act: -0.0001

Data Index: 277739 (C4 (Web Text))

Max Activating Token Index: 265