Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 16 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1013342 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0441. Min Act: -0.0003

Data Index: 808253 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0489. Min Act: -0.0003

Data Index: 649511 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0457. Min Act: -0.0003

Data Index: 340708 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0443. Min Act: -0.0003

Data Index: 387811 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0449. Min Act: -0.0003

Data Index: 161758 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0433. Min Act: -0.0003

Data Index: 310115 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1073662 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1167714 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0419. Min Act: -0.0003

Data Index: 921016 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1282028 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0399. Min Act: -0.0003

Data Index: 744223 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0429. Min Act: -0.0003

Data Index: 774521 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1042980 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0413. Min Act: -0.0003

Data Index: 608841 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0422. Min Act: -0.0003

Data Index: 191063 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0395. Min Act: -0.0003

Data Index: 369681 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0413. Min Act: -0.0003

Data Index: 775834 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0393. Min Act: -0.0003

Data Index: 930083 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0387. Min Act: -0.0003

Data Index: 434554 (C4 (Web Text))

Max Activating Token Index: 418