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

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

Neuron 4841 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1595139 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1218488 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7842. Min Act: -0.0000

Data Index: 846930 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1621692 (Python Code)

Max Activating Token Index: 650

Text #4

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7821. Min Act: -0.0000

Data Index: 337323 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1621068 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7843. Min Act: -0.0000

Data Index: 280939 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1489903 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7761. Min Act: -0.0000

Data Index: 592284 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7221. Min Act: -0.0000

Data Index: 772713 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1128257 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1390253 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7708. Min Act: -0.0000

Data Index: 309626 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7301. Min Act: -0.0001

Data Index: 1329444 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7042. Min Act: -0.0001

Data Index: 1637651 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7396. Min Act: -0.0000

Data Index: 880428 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1627709 (Python Code)

Max Activating Token Index: 919

Text #17

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1315812 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1590253 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1489664 (Python Code)

Max Activating Token Index: 364