Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1612 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0597. Min Act: -0.0006

Data Index: 1136470 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0618. Min Act: -0.0006

Data Index: 508007 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0610. Min Act: -0.0006

Data Index: 226519 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0584. Min Act: -0.0006

Data Index: 1312574 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1338314 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0580. Min Act: -0.0006

Data Index: 1152752 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0541. Min Act: -0.0006

Data Index: 1165258 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0576. Min Act: -0.0006

Data Index: 709883 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0562. Min Act: -0.0006

Data Index: 721053 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0569. Min Act: -0.0006

Data Index: 1240417 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0577. Min Act: -0.0006

Data Index: 537639 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0532. Min Act: -0.0006

Data Index: 1087740 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0551. Min Act: -0.0006

Data Index: 562210 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0555. Min Act: -0.0006

Data Index: 388457 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0540. Min Act: -0.0006

Data Index: 1202970 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0545. Min Act: -0.0006

Data Index: 1107995 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1316312 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0531. Min Act: -0.0006

Data Index: 47166 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0550. Min Act: -0.0006

Data Index: 1190323 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0618. Min Range: -0.0618

Max Act: 0.0517. Min Act: -0.0005

Data Index: 476431 (C4 (Web Text))

Max Activating Token Index: 486