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

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

Neuron 289 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: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0001

Data Index: 627613 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2389. Min Act: -0.0001

Data Index: 26162 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2320. Min Act: -0.0001

Data Index: 1277962 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0551. Min Act: -0.0001

Data Index: 549175 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1199084 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1519. Min Act: -0.0001

Data Index: 1001603 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1018. Min Act: -0.0001

Data Index: 941401 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1585. Min Act: -0.0001

Data Index: 915436 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0997. Min Act: -0.0001

Data Index: 441314 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0507. Min Act: -0.0001

Data Index: 1121038 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9317. Min Act: -0.0001

Data Index: 731008 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1219394 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1046. Min Act: -0.0001

Data Index: 456843 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0325. Min Act: -0.0001

Data Index: 917066 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0969. Min Act: -0.0001

Data Index: 473068 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0256. Min Act: -0.0001

Data Index: 413934 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9517. Min Act: -0.0001

Data Index: 870866 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0391. Min Act: -0.0001

Data Index: 914518 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9987. Min Act: -0.0001

Data Index: 981106 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9898. Min Act: -0.0001

Data Index: 576529 (C4 (Web Text))

Max Activating Token Index: 111