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

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

Neuron 402 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1387. Min Act: -0.0002

Data Index: 165111 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1450. Min Act: -0.0003

Data Index: 955121 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1358. Min Act: -0.0002

Data Index: 758947 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1298. Min Act: -0.0002

Data Index: 574712 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1349. Min Act: -0.0002

Data Index: 784472 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1141. Min Act: -0.0002

Data Index: 975984 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0988. Min Act: -0.0002

Data Index: 624806 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1203. Min Act: -0.0002

Data Index: 1128148 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1082. Min Act: -0.0002

Data Index: 590461 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0876. Min Act: -0.0002

Data Index: 911011 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0716. Min Act: -0.0002

Data Index: 596545 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.1235. Min Act: -0.0002

Data Index: 840843 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0761. Min Act: -0.0002

Data Index: 623434 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0743. Min Act: -0.0002

Data Index: 1189681 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0617. Min Act: -0.0002

Data Index: 371302 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0555. Min Act: -0.0002

Data Index: 1328256 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0251. Min Act: -0.0002

Data Index: 708560 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0564. Min Act: -0.0002

Data Index: 642116 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0412. Min Act: -0.0003

Data Index: 684623 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.1450. Min Range: -1.1450

Max Act: 1.0732. Min Act: -0.0002

Data Index: 1162866 (C4 (Web Text))

Max Activating Token Index: 734