Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4311 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5604. Min Act: -0.0000

Data Index: 301712 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5163. Min Act: -0.0000

Data Index: 636500 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5458. Min Act: 0.0000

Data Index: 1596315 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1478577 (Python Code)

Max Activating Token Index: 358

Text #4

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1369244 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1601871 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1595723 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1553738 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5125. Min Act: -0.0000

Data Index: 700680 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4874. Min Act: -0.0000

Data Index: 601538 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1090263 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4749. Min Act: -0.0000

Data Index: 189337 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4687. Min Act: -0.0000

Data Index: 657205 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1371648 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4601. Min Act: -0.0000

Data Index: 605111 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1391529 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1554200 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1617263 (Python Code)

Max Activating Token Index: 982

Text #18

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4260. Min Act: -0.0000

Data Index: 140323 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4230. Min Act: -0.0000

Data Index: 11516 (C4 (Web Text))

Max Activating Token Index: 980