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

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

Neuron 3480 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: 5.2224. Min Range: -5.2224

Max Act: 4.5225. Min Act: -0.0000

Data Index: 516774 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 5.2224. Min Range: -5.2224

Max Act: 5.0355. Min Act: -0.0000

Data Index: 635569 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.9585. Min Act: -0.0000

Data Index: 998929 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.9583. Min Act: -0.0000

Data Index: 20250 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.8307. Min Act: -0.0000

Data Index: 1558469 (Python Code)

Max Activating Token Index: 948

Text #5

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.7838. Min Act: -0.0000

Data Index: 475497 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.7978. Min Act: -0.0000

Data Index: 662291 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.6993. Min Act: -0.0000

Data Index: 592554 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.6432. Min Act: -0.0000

Data Index: 337783 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.5012. Min Act: -0.0000

Data Index: 429349 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.3974. Min Act: -0.0000

Data Index: 270166 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 5.2224. Min Range: -5.2224

Max Act: 5.1045. Min Act: -0.0000

Data Index: 1351353 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.8901. Min Act: -0.0000

Data Index: 981200 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.5212. Min Act: -0.0000

Data Index: 294840 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.8744. Min Act: -0.0000

Data Index: 1612845 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.4012. Min Act: -0.0000

Data Index: 1019115 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.6200. Min Act: -0.0000

Data Index: 1104878 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.7580. Min Act: -0.0000

Data Index: 408276 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.2224. Min Range: -5.2224

Max Act: 4.4849. Min Act: -0.0000

Data Index: 45141 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 5.2224. Min Range: -5.2224

Max Act: 5.2224. Min Act: -0.0000

Data Index: 858762 (C4 (Web Text))

Max Activating Token Index: 817