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

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

Neuron 4758 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1578412 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1491943 (Python Code)

Max Activating Token Index: 994

Text #2

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1482539 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5512. Min Act: -0.0001

Data Index: 1288900 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1482680 (Python Code)

Max Activating Token Index: 355

Text #5

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5523. Min Act: -0.0001

Data Index: 1625773 (Python Code)

Max Activating Token Index: 282

Text #6

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4981. Min Act: -0.0001

Data Index: 204969 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5154. Min Act: -0.0001

Data Index: 869510 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5287. Min Act: -0.0001

Data Index: 580114 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1395038 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5286. Min Act: -0.0001

Data Index: 1309478 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1415920 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5116. Min Act: -0.0001

Data Index: 1646564 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4828. Min Act: -0.0001

Data Index: 404645 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5014. Min Act: -0.0001

Data Index: 72460 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4818. Min Act: -0.0001

Data Index: 514627 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4981. Min Act: -0.0001

Data Index: 851956 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1637487 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1536789 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 0.6631. Min Range: -0.6631

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1465869 (Python Code)

Max Activating Token Index: 36