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

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

Neuron 777 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: 0.1008. Min Range: -0.1008

Max Act: 0.1008. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0693. Min Act: -0.0000

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1195615 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0494. Min Act: -0.0001

Data Index: 976403 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0491. Min Act: -0.0001

Data Index: 266496 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1173572 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0479. Min Act: -0.0000

Data Index: 953854 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0427. Min Act: -0.0000

Data Index: 898452 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1320756 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0385. Min Act: -0.0001

Data Index: 479456 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0442. Min Act: -0.0001

Data Index: 374197 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0407. Min Act: -0.0000

Data Index: 768261 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0430. Min Act: -0.0001

Data Index: 974101 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0368. Min Act: -0.0001

Data Index: 736713 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0377. Min Act: -0.0001

Data Index: 484021 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0408. Min Act: -0.0001

Data Index: 812345 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0432. Min Act: -0.0001

Data Index: 925917 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0408. Min Act: -0.0000

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0401. Min Act: -0.0001

Data Index: 67536 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.1008. Min Range: -0.1008

Max Act: 0.0386. Min Act: -0.0001

Data Index: 159508 (C4 (Web Text))

Max Activating Token Index: 786