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

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

Neuron 2006 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: 0.0590. Min Range: -0.0590

Max Act: 0.0590. Min Act: -0.0005

Data Index: 1084341 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0555. Min Act: -0.0005

Data Index: 178760 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0524. Min Act: -0.0005

Data Index: 451303 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0531. Min Act: -0.0005

Data Index: 1313293 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0510. Min Act: -0.0005

Data Index: 959779 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0500. Min Act: -0.0005

Data Index: 1339961 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0515. Min Act: -0.0005

Data Index: 630580 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0495. Min Act: -0.0005

Data Index: 844643 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0488. Min Act: -0.0005

Data Index: 77579 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0505. Min Act: -0.0005

Data Index: 1270316 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0486. Min Act: -0.0005

Data Index: 152874 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0497. Min Act: -0.0005

Data Index: 170788 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0479. Min Act: -0.0005

Data Index: 1126999 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0506. Min Act: -0.0005

Data Index: 1084574 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0499. Min Act: -0.0005

Data Index: 660023 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0491. Min Act: -0.0005

Data Index: 21739 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0472. Min Act: -0.0005

Data Index: 946496 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0487. Min Act: -0.0005

Data Index: 120829 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0487. Min Act: -0.0005

Data Index: 841648 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0492. Min Act: -0.0005

Data Index: 118329 (C4 (Web Text))

Max Activating Token Index: 508