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

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

Neuron 4449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1232600 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1086148 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1695. Min Act: -0.0000

Data Index: 491853 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1573. Min Act: -0.0000

Data Index: 770796 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: -0.0000

Data Index: 133102 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1660. Min Act: -0.0000

Data Index: 549869 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1523. Min Act: -0.0000

Data Index: 366811 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1575. Min Act: -0.0000

Data Index: 128457 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1602. Min Act: -0.0000

Data Index: 297028 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1549. Min Act: -0.0000

Data Index: 904621 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1543. Min Act: -0.0000

Data Index: 26408 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1593. Min Act: -0.0000

Data Index: 555883 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1511. Min Act: -0.0000

Data Index: 816089 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1514. Min Act: -0.0000

Data Index: 648265 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1499. Min Act: -0.0000

Data Index: 648405 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1500. Min Act: -0.0000

Data Index: 524975 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1445. Min Act: -0.0000

Data Index: 900705 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1443. Min Act: -0.0000

Data Index: 887693 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1227433 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1444. Min Act: -0.0000

Data Index: 424082 (C4 (Web Text))

Max Activating Token Index: 697