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

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

Neuron 1619 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2608. Min Act: -0.0002

Data Index: 327544 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2438. Min Act: -0.0002

Data Index: 1235392 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2405. Min Act: -0.0002

Data Index: 233501 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2393. Min Act: -0.0002

Data Index: 842455 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2468. Min Act: -0.0001

Data Index: 169777 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2324. Min Act: -0.0002

Data Index: 96374 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2312. Min Act: -0.0002

Data Index: 180441 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2222. Min Act: -0.0001

Data Index: 988587 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2226. Min Act: -0.0002

Data Index: 809646 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2220. Min Act: -0.0002

Data Index: 1173926 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2147. Min Act: -0.0001

Data Index: 95222 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2097. Min Act: -0.0002

Data Index: 453214 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1359623 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2132. Min Act: -0.0002

Data Index: 275817 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2055. Min Act: -0.0002

Data Index: 927411 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2114. Min Act: -0.0002

Data Index: 641864 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2018. Min Act: -0.0001

Data Index: 898735 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1149369 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2056. Min Act: -0.0001

Data Index: 155555 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2125. Min Act: -0.0001

Data Index: 567329 (C4 (Web Text))

Max Activating Token Index: 92