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

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

Neuron 4750 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3862. Min Act: -0.0001

Data Index: 128359 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3442. Min Act: -0.0001

Data Index: 640786 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3188. Min Act: -0.0001

Data Index: 567750 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3155. Min Act: -0.0001

Data Index: 791698 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3351. Min Act: -0.0001

Data Index: 996487 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2988. Min Act: -0.0001

Data Index: 830365 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3099. Min Act: -0.0001

Data Index: 480381 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3206. Min Act: -0.0001

Data Index: 618366 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3079. Min Act: -0.0001

Data Index: 76764 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3255. Min Act: -0.0001

Data Index: 900714 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1114499 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2778. Min Act: -0.0001

Data Index: 438822 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2729. Min Act: -0.0001

Data Index: 235706 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2734. Min Act: -0.0001

Data Index: 1054979 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2784. Min Act: -0.0001

Data Index: 90241 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2375. Min Act: -0.0001

Data Index: 776261 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1148205 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2350. Min Act: -0.0001

Data Index: 440216 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2399. Min Act: -0.0001

Data Index: 828725 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2154. Min Act: -0.0001

Data Index: 260865 (C4 (Web Text))

Max Activating Token Index: 171