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

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

Neuron 916 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8658. Min Act: -0.0000

Data Index: 687401 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1254532 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 1.1773. Min Range: -1.1773

Max Act: 1.1773. Min Act: -0.0000

Data Index: 21097 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.8383. Min Act: -0.0000

Data Index: 585686 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1267202 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.6249. Min Act: -0.0000

Data Index: 560480 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.6655. Min Act: -0.0000

Data Index: 91321 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5668. Min Act: 0.0000

Data Index: 1340408 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5792. Min Act: 0.0000

Data Index: 933063 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5665. Min Act: -0.0000

Data Index: 4452 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5669. Min Act: 0.0000

Data Index: 918789 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5300. Min Act: -0.0000

Data Index: 355659 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5684. Min Act: 0.0000

Data Index: 858421 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5116. Min Act: -0.0000

Data Index: 63296 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5202. Min Act: -0.0000

Data Index: 119157 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5149. Min Act: 0.0000

Data Index: 1155035 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5160. Min Act: 0.0000

Data Index: 1081519 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5155. Min Act: 0.0000

Data Index: 650082 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1043131 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.1773. Min Range: -1.1773

Max Act: 0.5202. Min Act: -0.0000

Data Index: 413965 (C4 (Web Text))

Max Activating Token Index: 899