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

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

Neuron 3443 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0001

Data Index: 657692 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1194. Min Act: -0.0001

Data Index: 132860 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1061. Min Act: -0.0001

Data Index: 682005 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1476910 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0847. Min Act: -0.0001

Data Index: 150118 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0992. Min Act: -0.0001

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1577897 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0794. Min Act: -0.0001

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0990. Min Act: -0.0001

Data Index: 403981 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0937. Min Act: -0.0001

Data Index: 553470 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1462988 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1601302 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1366022 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0810. Min Act: -0.0001

Data Index: 829022 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1418835 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1184891 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0816. Min Act: -0.0001

Data Index: 889261 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0831. Min Act: -0.0001

Data Index: 535472 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1556681 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.0930. Min Act: -0.0001

Data Index: 361416 (C4 (Web Text))

Max Activating Token Index: 88