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

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

Neuron 3216 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: 2.8138. Min Range: -2.8138

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1153138 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.5792. Min Act: -0.0000

Data Index: 368483 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.4002. Min Act: -0.0000

Data Index: 797989 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.3982. Min Act: -0.0000

Data Index: 719469 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.2533. Min Act: -0.0000

Data Index: 1080632 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.6140. Min Act: -0.0000

Data Index: 45467 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.1948. Min Act: -0.0000

Data Index: 177792 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.4580. Min Act: -0.0000

Data Index: 1136500 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.4230. Min Act: -0.0000

Data Index: 309829 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.4360. Min Act: -0.0000

Data Index: 103159 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.4285. Min Act: -0.0000

Data Index: 174942 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.2789. Min Act: -0.0000

Data Index: 506673 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.2244. Min Act: -0.0000

Data Index: 979505 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.4796. Min Act: -0.0000

Data Index: 717421 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.0829. Min Act: -0.0000

Data Index: 1248522 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.0980. Min Act: -0.0000

Data Index: 734552 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.1799. Min Act: -0.0000

Data Index: 510949 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.0298. Min Act: -0.0000

Data Index: 682120 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1309251 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.1308. Min Act: -0.0000

Data Index: 812645 (C4 (Web Text))

Max Activating Token Index: 671