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

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

Neuron 4537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0000

Data Index: 559186 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0687. Min Act: -0.0001

Data Index: 315281 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1179704 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1319318 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0571. Min Act: -0.0000

Data Index: 439036 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1222653 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1319452 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1351329 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1018711 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0541. Min Act: -0.0001

Data Index: 472258 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0566. Min Act: -0.0001

Data Index: 137428 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0485. Min Act: -0.0001

Data Index: 747856 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0512. Min Act: -0.0000

Data Index: 944978 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0527. Min Act: -0.0001

Data Index: 41230 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0550. Min Act: -0.0001

Data Index: 157862 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0537. Min Act: -0.0001

Data Index: 163279 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1002910 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0466. Min Act: -0.0001

Data Index: 351859 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0509. Min Act: -0.0001

Data Index: 775313 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0495. Min Act: -0.0001

Data Index: 301298 (C4 (Web Text))

Max Activating Token Index: 429