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

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

Neuron 2374 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: 0.2854. Min Range: -0.2854

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1020147 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2733. Min Act: -0.0000

Data Index: 295131 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2717. Min Act: -0.0001

Data Index: 514665 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2554. Min Act: -0.0001

Data Index: 930635 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1218465 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2832. Min Act: -0.0001

Data Index: 732465 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2695. Min Act: -0.0000

Data Index: 918556 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2479. Min Act: -0.0000

Data Index: 670082 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2642. Min Act: -0.0000

Data Index: 383251 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2304. Min Act: -0.0000

Data Index: 961558 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2541. Min Act: -0.0000

Data Index: 958935 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2520. Min Act: -0.0001

Data Index: 884211 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2503. Min Act: -0.0001

Data Index: 709146 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1247945 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1022929 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2551. Min Act: -0.0001

Data Index: 289015 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2128. Min Act: -0.0001

Data Index: 8740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2581. Min Act: -0.0000

Data Index: 142453 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2091. Min Act: -0.0001

Data Index: 621154 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2139. Min Act: -0.0001

Data Index: 385443 (C4 (Web Text))

Max Activating Token Index: 516