Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2627 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 433709 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1397. Min Act: -0.0001

Data Index: 975273 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1561. Min Act: -0.0001

Data Index: 8699 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1308825 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1409. Min Act: -0.0001

Data Index: 69779 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1341. Min Act: -0.0001

Data Index: 185323 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1030544 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1401. Min Act: -0.0002

Data Index: 867464 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1341. Min Act: -0.0002

Data Index: 472155 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1091. Min Act: -0.0001

Data Index: 553713 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1118. Min Act: -0.0001

Data Index: 898574 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1260748 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0996. Min Act: -0.0002

Data Index: 489605 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1011. Min Act: -0.0002

Data Index: 290052 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1104. Min Act: -0.0002

Data Index: 791043 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1189824 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1082. Min Act: -0.0002

Data Index: 103289 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1038. Min Act: -0.0001

Data Index: 85254 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1027. Min Act: -0.0002

Data Index: 562913 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.0991. Min Act: -0.0002

Data Index: 463964 (C4 (Web Text))

Max Activating Token Index: 188