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

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

Neuron 5906 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1266226 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1645. Min Act: -0.0001

Data Index: 239362 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1671. Min Act: -0.0001

Data Index: 707453 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1641. Min Act: -0.0001

Data Index: 343440 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1682. Min Act: -0.0001

Data Index: 72897 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1501. Min Act: -0.0001

Data Index: 621221 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1640. Min Act: -0.0001

Data Index: 470295 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1639. Min Act: -0.0001

Data Index: 615763 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1446. Min Act: -0.0001

Data Index: 891269 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1678. Min Act: -0.0001

Data Index: 944045 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1518. Min Act: -0.0001

Data Index: 267936 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1557. Min Act: -0.0001

Data Index: 790101 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1555. Min Act: -0.0001

Data Index: 813487 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1502. Min Act: -0.0001

Data Index: 701172 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1620. Min Act: -0.0001

Data Index: 550769 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1009084 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1492. Min Act: -0.0001

Data Index: 546741 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1530. Min Act: -0.0001

Data Index: 649172 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1447. Min Act: -0.0001

Data Index: 908493 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1587. Min Act: -0.0001

Data Index: 75156 (C4 (Web Text))

Max Activating Token Index: 114