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

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

Neuron 3583 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: 0.4365. Min Range: -0.4365

Max Act: 0.4365. Min Act: -0.0001

Data Index: 1136690 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4331. Min Act: -0.0001

Data Index: 215877 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4034. Min Act: -0.0001

Data Index: 309426 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3740. Min Act: -0.0001

Data Index: 394135 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3573. Min Act: -0.0001

Data Index: 324531 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.4319. Min Act: -0.0001

Data Index: 429486 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3752. Min Act: -0.0001

Data Index: 483036 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3987. Min Act: -0.0001

Data Index: 673698 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3680. Min Act: -0.0001

Data Index: 443552 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3462. Min Act: -0.0001

Data Index: 395123 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3475. Min Act: -0.0001

Data Index: 1078117 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1207000 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3252. Min Act: -0.0001

Data Index: 768250 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1162855 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3566. Min Act: -0.0001

Data Index: 956078 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3416. Min Act: -0.0001

Data Index: 33753 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3480. Min Act: -0.0001

Data Index: 1111614 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3708. Min Act: -0.0001

Data Index: 264173 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3344. Min Act: -0.0001

Data Index: 541600 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.4365. Min Range: -0.4365

Max Act: 0.3212. Min Act: -0.0001

Data Index: 563220 (C4 (Web Text))

Max Activating Token Index: 136