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

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

Neuron 2825 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6494. Min Range: -2.6494

Max Act: 2.6494. Min Act: -0.0000

Data Index: 557389 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.6494. Min Range: -2.6494

Max Act: 2.3835. Min Act: -0.0000

Data Index: 1617727 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 2.6494. Min Range: -2.6494

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1493476 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.8299. Min Act: -0.0000

Data Index: 1601777 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.8939. Min Act: -0.0000

Data Index: 1257651 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7857. Min Act: -0.0000

Data Index: 391576 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1481589 (Python Code)

Max Activating Token Index: 431

Text #7

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1348021 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.8907. Min Act: -0.0000

Data Index: 331294 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.6297. Min Act: -0.0000

Data Index: 249641 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1333234 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7447. Min Act: -0.0000

Data Index: 1419791 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.6414. Min Act: -0.0000

Data Index: 882742 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.8451. Min Act: -0.0000

Data Index: 828496 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1081800 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.8328. Min Act: -0.0000

Data Index: 13419 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7772. Min Act: -0.0000

Data Index: 774554 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7583. Min Act: -0.0000

Data Index: 269657 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.5812. Min Act: -0.0000

Data Index: 826361 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 2.6494. Min Range: -2.6494

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1277794 (C4 (Web Text))

Max Activating Token Index: 377