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

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

Neuron 5497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0249. Min Range: -5.0249

Max Act: 5.0249. Min Act: -0.0000

Data Index: 506145 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.6892. Min Act: -0.0000

Data Index: 1346115 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.5817. Min Act: -0.0000

Data Index: 513594 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.5759. Min Act: -0.0000

Data Index: 46366 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.4606. Min Act: -0.0000

Data Index: 504592 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.0937. Min Act: -0.0000

Data Index: 134337 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.2092. Min Act: -0.0000

Data Index: 1221343 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 5.0249. Min Range: -5.0249

Max Act: 4.1158. Min Act: -0.0000

Data Index: 257315 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.9200. Min Act: -0.0000

Data Index: 1304182 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.7217. Min Act: -0.0000

Data Index: 1096175 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.6690. Min Act: -0.0000

Data Index: 576495 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.5836. Min Act: -0.0000

Data Index: 930463 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.2631. Min Act: -0.0000

Data Index: 909087 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.6784. Min Act: -0.0000

Data Index: 521400 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.6613. Min Act: -0.0000

Data Index: 235610 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1111720 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.0892. Min Act: -0.0000

Data Index: 967689 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 5.0249. Min Range: -5.0249

Max Act: 2.7268. Min Act: -0.0000

Data Index: 321980 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.0454. Min Act: -0.0000

Data Index: 1325883 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 5.0249. Min Range: -5.0249

Max Act: 3.0134. Min Act: -0.0000

Data Index: 876231 (C4 (Web Text))

Max Activating Token Index: 520