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

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

Neuron 3089 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4668. Min Act: -0.0001

Data Index: 1652611 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1549104 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4279. Min Act: -0.0001

Data Index: 1436665 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4199. Min Act: -0.0001

Data Index: 1417391 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1464677 (Python Code)

Max Activating Token Index: 627

Text #5

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4165. Min Act: -0.0001

Data Index: 1430047 (Python Code)

Max Activating Token Index: 750

Text #6

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3870. Min Act: -0.0001

Data Index: 1442604 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4134. Min Act: -0.0001

Data Index: 1547329 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4014. Min Act: -0.0001

Data Index: 1367161 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1459081 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1376441 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3649. Min Act: -0.0001

Data Index: 1484431 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1417053 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3855. Min Act: -0.0001

Data Index: 1462722 (Python Code)

Max Activating Token Index: 353

Text #14

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4080. Min Act: -0.0001

Data Index: 1515688 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4106. Min Act: -0.0001

Data Index: 1378804 (Python Code)

Max Activating Token Index: 609

Text #16

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1489471 (Python Code)

Max Activating Token Index: 841

Text #17

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3972. Min Act: -0.0001

Data Index: 1557458 (Python Code)

Max Activating Token Index: 394

Text #18

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1396593 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3918. Min Act: -0.0001

Data Index: 1528618 (Python Code)

Max Activating Token Index: 307