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

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

Neuron 3994 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: 2.8222. Min Range: -2.8222

Max Act: 2.7271. Min Act: -0.0001

Data Index: 1656405 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.3622. Min Act: -0.0000

Data Index: 1375210 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.4772. Min Act: -0.0000

Data Index: 1646413 (Python Code)

Max Activating Token Index: 752

Text #3

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.8222. Min Act: -0.0001

Data Index: 1551715 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.6321. Min Act: -0.0000

Data Index: 1517883 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.5102. Min Act: -0.0001

Data Index: 1479461 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.5053. Min Act: -0.0000

Data Index: 1524477 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1399723 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.3628. Min Act: -0.0000

Data Index: 1554189 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.4769. Min Act: -0.0000

Data Index: 1486692 (Python Code)

Max Activating Token Index: 849

Text #10

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.5136. Min Act: -0.0001

Data Index: 1370982 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.5103. Min Act: -0.0000

Data Index: 1431716 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.2582. Min Act: -0.0000

Data Index: 1436889 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.3826. Min Act: -0.0000

Data Index: 1528299 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.1194. Min Act: -0.0000

Data Index: 1383715 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.3892. Min Act: -0.0001

Data Index: 1631464 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.3925. Min Act: -0.0001

Data Index: 1574492 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.2632. Min Act: -0.0000

Data Index: 1563576 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.4906. Min Act: -0.0001

Data Index: 1396352 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 2.8222. Min Range: -2.8222

Max Act: 2.0462. Min Act: -0.0001

Data Index: 1512036 (Python Code)

Max Activating Token Index: 92