Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.2046. Min Act: -0.0001

Data Index: 504049 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.3279. Min Act: -0.0001

Data Index: 707718 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.2308. Min Act: -0.0001

Data Index: 227180 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.3023. Min Act: -0.0001

Data Index: 44760 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.2756. Min Act: -0.0001

Data Index: 1355808 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.2826. Min Act: -0.0001

Data Index: 20277 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1045435 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1931. Min Act: -0.0000

Data Index: 690539 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.2427. Min Act: -0.0000

Data Index: 450408 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1472. Min Act: -0.0001

Data Index: 928896 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1323. Min Act: -0.0000

Data Index: 73383 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1020. Min Act: -0.0000

Data Index: 45532 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1006294 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1552. Min Act: -0.0000

Data Index: 394440 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1867. Min Act: -0.0001

Data Index: 1216084 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1841. Min Act: -0.0000

Data Index: 293432 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1624. Min Act: -0.0000

Data Index: 964858 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.2064. Min Act: -0.0000

Data Index: 438628 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1491. Min Act: -0.0001

Data Index: 838750 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.3279. Min Range: -1.3279

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1163180 (C4 (Web Text))

Max Activating Token Index: 503