Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3777 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.2910. Min Range: -5.2910

Max Act: 5.2910. Min Act: -0.0001

Data Index: 238489 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 5.2910. Min Range: -5.2910

Max Act: 5.1336. Min Act: -0.0001

Data Index: 828433 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.7627. Min Act: -0.0001

Data Index: 559656 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.7018. Min Act: -0.0001

Data Index: 1022848 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 5.2910. Min Range: -5.2910

Max Act: 5.1058. Min Act: -0.0001

Data Index: 635628 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.6521. Min Act: -0.0001

Data Index: 921097 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.6375. Min Act: -0.0001

Data Index: 27330 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.4491. Min Act: -0.0001

Data Index: 1039959 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.4246. Min Act: -0.0001

Data Index: 1002850 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 5.2910. Min Range: -5.2910

Max Act: 5.0936. Min Act: -0.0001

Data Index: 1318203 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.6523. Min Act: -0.0001

Data Index: 374376 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.1327. Min Act: -0.0001

Data Index: 958122 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.4802. Min Act: -0.0001

Data Index: 391712 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.1278. Min Act: -0.0001

Data Index: 473515 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.0896. Min Act: -0.0001

Data Index: 908562 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.5237. Min Act: -0.0001

Data Index: 501399 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.5034. Min Act: -0.0001

Data Index: 117799 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.2032. Min Act: -0.0001

Data Index: 1200477 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.1308. Min Act: -0.0001

Data Index: 337221 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 5.2910. Min Range: -5.2910

Max Act: 4.3194. Min Act: -0.0001

Data Index: 419833 (C4 (Web Text))

Max Activating Token Index: 101