Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4705 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1517. Min Range: -2.1517

Max Act: 2.1517. Min Act: -0.0000

Data Index: 1298367 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 2.1517. Min Range: -2.1517

Max Act: 2.1128. Min Act: -0.0000

Data Index: 3920 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.9839. Min Act: -0.0000

Data Index: 1124167 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.8064. Min Act: -0.0000

Data Index: 1640659 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.7279. Min Act: -0.0000

Data Index: 1321088 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.8264. Min Act: 0.0000

Data Index: 382715 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1264464 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1592979 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1131381 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4815. Min Act: -0.0000

Data Index: 872381 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4616. Min Act: -0.0000

Data Index: 546080 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4779. Min Act: 0.0000

Data Index: 371939 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4641. Min Act: -0.0000

Data Index: 302900 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4740. Min Act: 0.0000

Data Index: 663466 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4666. Min Act: 0.0000

Data Index: 337721 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4398. Min Act: -0.0000

Data Index: 585981 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1482996 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1375773 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1594707 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 2.1517. Min Range: -2.1517

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1475406 (Python Code)

Max Activating Token Index: 809