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

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

Neuron 4775 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: 2.1092. Min Range: -2.1092

Max Act: 2.1092. Min Act: -0.0000

Data Index: 1485355 (Python Code)

Max Activating Token Index: 912

Text #1

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.6187. Min Act: -0.0000

Data Index: 1567229 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.7062. Min Act: -0.0000

Data Index: 327841 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.6879. Min Act: -0.0000

Data Index: 276371 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1395038 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.6625. Min Act: -0.0000

Data Index: 1398667 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1413222 (Python Code)

Max Activating Token Index: 702

Text #7

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.7059. Min Act: -0.0000

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.5854. Min Act: -0.0000

Data Index: 866421 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.4826. Min Act: -0.0000

Data Index: 358444 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.6367. Min Act: -0.0000

Data Index: 1634706 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.4743. Min Act: -0.0000

Data Index: 410435 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.4031. Min Act: -0.0000

Data Index: 324247 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1391042 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.4120. Min Act: -0.0000

Data Index: 861259 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.5953. Min Act: -0.0000

Data Index: 953372 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.3410. Min Act: -0.0000

Data Index: 189030 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.5510. Min Act: -0.0000

Data Index: 735238 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.5020. Min Act: -0.0000

Data Index: 596700 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 2.1092. Min Range: -2.1092

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1625773 (Python Code)

Max Activating Token Index: 220