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

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

Neuron 3415 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: 0.1050. Min Range: -0.1050

Max Act: 0.1050. Min Act: -0.0001

Data Index: 494976 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1176109 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0552. Min Act: -0.0001

Data Index: 720284 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1121116 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1249529 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0619. Min Act: -0.0001

Data Index: 331730 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0569. Min Act: -0.0001

Data Index: 411543 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0550. Min Act: -0.0001

Data Index: 88360 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1243724 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0555. Min Act: -0.0001

Data Index: 411518 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1312539 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0498. Min Act: -0.0001

Data Index: 586165 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0534. Min Act: -0.0001

Data Index: 904042 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0590. Min Act: -0.0001

Data Index: 417567 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0541. Min Act: -0.0001

Data Index: 416299 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1172102 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1142923 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0482. Min Act: -0.0001

Data Index: 360304 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0508. Min Act: -0.0001

Data Index: 390390 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0482. Min Act: -0.0001

Data Index: 2857 (C4 (Web Text))

Max Activating Token Index: 185