Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0005

Data Index: 253467 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0553. Min Act: -0.0005

Data Index: 728765 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0586. Min Act: -0.0005

Data Index: 1138885 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0564. Min Act: -0.0005

Data Index: 542974 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0584. Min Act: -0.0005

Data Index: 162652 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0534. Min Act: -0.0005

Data Index: 555509 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0475. Min Act: -0.0005

Data Index: 926846 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0491. Min Act: -0.0005

Data Index: 194921 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0517. Min Act: -0.0005

Data Index: 1087 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0509. Min Act: -0.0005

Data Index: 411259 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0506. Min Act: -0.0005

Data Index: 983717 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0490. Min Act: -0.0005

Data Index: 1190884 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0498. Min Act: -0.0005

Data Index: 378433 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0517. Min Act: -0.0005

Data Index: 158786 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0549. Min Act: -0.0005

Data Index: 1338828 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0491. Min Act: -0.0005

Data Index: 1286881 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0521. Min Act: -0.0005

Data Index: 963641 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0488. Min Act: -0.0005

Data Index: 713486 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0448. Min Act: -0.0005

Data Index: 20814 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0486. Min Act: -0.0005

Data Index: 1021521 (C4 (Web Text))

Max Activating Token Index: 772