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

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

Neuron 2932 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0598. Min Range: -1.0598

Max Act: 1.0292. Min Act: -0.0000

Data Index: 14382 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9810. Min Act: -0.0000

Data Index: 910013 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.0598. Min Range: -1.0598

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1080735 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9547. Min Act: -0.0000

Data Index: 149677 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1189553 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9318. Min Act: -0.0000

Data Index: 815308 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1191241 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8647. Min Act: -0.0000

Data Index: 676222 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9108. Min Act: -0.0000

Data Index: 628899 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8500. Min Act: -0.0000

Data Index: 425940 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1243333 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.9329. Min Act: -0.0000

Data Index: 944651 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8757. Min Act: -0.0000

Data Index: 466342 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1015454 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8446. Min Act: -0.0000

Data Index: 828446 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8105. Min Act: -0.0000

Data Index: 779131 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8654. Min Act: -0.0000

Data Index: 346354 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8244. Min Act: -0.0000

Data Index: 349274 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8356. Min Act: -0.0000

Data Index: 612649 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.0598. Min Range: -1.0598

Max Act: 0.8065. Min Act: -0.0000

Data Index: 737878 (C4 (Web Text))

Max Activating Token Index: 507