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

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

Neuron 3637 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.9838. Min Act: -0.0000

Data Index: 912659 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.8401. Min Act: -0.0000

Data Index: 909534 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.8108. Min Act: -0.0000

Data Index: 940441 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.7908. Min Act: -0.0000

Data Index: 468219 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.5825. Min Act: -0.0000

Data Index: 1032441 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 4.0510. Min Range: -4.0510

Max Act: 4.0510. Min Act: -0.0000

Data Index: 1347266 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.8565. Min Act: -0.0000

Data Index: 1227922 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.8344. Min Act: -0.0000

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.6465. Min Act: -0.0000

Data Index: 738901 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.7905. Min Act: -0.0000

Data Index: 1065371 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.6713. Min Act: -0.0000

Data Index: 241929 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.5385. Min Act: -0.0000

Data Index: 564309 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.3303. Min Act: -0.0000

Data Index: 133013 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.4891. Min Act: -0.0000

Data Index: 968316 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.4902. Min Act: -0.0000

Data Index: 51324 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.7653. Min Act: -0.0000

Data Index: 59778 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.7687. Min Act: -0.0000

Data Index: 12140 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.7944. Min Act: -0.0000

Data Index: 344958 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.4582. Min Act: -0.0000

Data Index: 22518 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 4.0510. Min Range: -4.0510

Max Act: 3.4391. Min Act: -0.0000

Data Index: 1334226 (C4 (Web Text))

Max Activating Token Index: 461