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

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

Neuron 4270 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7980. Min Act: -0.0000

Data Index: 531004 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6392. Min Act: -0.0001

Data Index: 779440 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7162. Min Act: -0.0001

Data Index: 402846 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7460. Min Act: -0.0000

Data Index: 893194 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6504. Min Act: -0.0001

Data Index: 612694 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1147181 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6970. Min Act: -0.0001

Data Index: 21959 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6358. Min Act: -0.0001

Data Index: 408000 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1120328 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1350069 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6608. Min Act: -0.0001

Data Index: 1345365 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6149. Min Act: -0.0000

Data Index: 807089 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6541. Min Act: -0.0001

Data Index: 206472 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6461. Min Act: -0.0000

Data Index: 191117 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6245. Min Act: -0.0000

Data Index: 975934 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6030. Min Act: -0.0000

Data Index: 69628 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6473. Min Act: -0.0001

Data Index: 1346412 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6988. Min Act: -0.0001

Data Index: 944571 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6365. Min Act: -0.0000

Data Index: 387122 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6302. Min Act: -0.0000

Data Index: 101225 (C4 (Web Text))

Max Activating Token Index: 305