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

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

Neuron 3014 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.8039. Min Act: -0.0001

Data Index: 1041384 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.6028. Min Act: -0.0001

Data Index: 1309232 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.4439. Min Act: -0.0001

Data Index: 235129 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.3156. Min Act: -0.0001

Data Index: 617020 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.3873. Min Act: -0.0001

Data Index: 1151735 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.2274. Min Act: -0.0001

Data Index: 189100 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1348963 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.2719. Min Act: -0.0001

Data Index: 411471 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1594. Min Act: -0.0001

Data Index: 1113040 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1175254 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1303. Min Act: -0.0001

Data Index: 50865 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1139. Min Act: -0.0000

Data Index: 684318 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.0487. Min Act: -0.0000

Data Index: 855214 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1358. Min Act: -0.0001

Data Index: 195686 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1720. Min Act: -0.0001

Data Index: 416929 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1519. Min Act: -0.0001

Data Index: 301806 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.1416. Min Act: -0.0001

Data Index: 933869 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.0802. Min Act: -0.0000

Data Index: 116347 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.8039. Min Range: -1.8039

Max Act: 1.0607. Min Act: -0.0001

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 1.8039. Min Range: -1.8039

Max Act: 0.9993. Min Act: -0.0000

Data Index: 776862 (C4 (Web Text))

Max Activating Token Index: 823