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

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

Neuron 1585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0006

Data Index: 213545 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0499. Min Act: -0.0006

Data Index: 506171 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0544. Min Act: -0.0006

Data Index: 976886 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0427. Min Act: -0.0006

Data Index: 1289585 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0470. Min Act: -0.0006

Data Index: 918251 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1048584 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0505. Min Act: -0.0006

Data Index: 34162 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0440. Min Act: -0.0006

Data Index: 348432 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0403. Min Act: -0.0006

Data Index: 1188930 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0372. Min Act: -0.0006

Data Index: 184316 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1352056 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0369. Min Act: -0.0006

Data Index: 833652 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0371. Min Act: -0.0006

Data Index: 650048 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0362. Min Act: -0.0006

Data Index: 737789 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0382. Min Act: -0.0006

Data Index: 856571 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0387. Min Act: -0.0006

Data Index: 959025 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0386. Min Act: -0.0006

Data Index: 202333 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0278. Min Act: -0.0006

Data Index: 749845 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0376. Min Act: -0.0006

Data Index: 369871 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0350. Min Act: -0.0006

Data Index: 518088 (C4 (Web Text))

Max Activating Token Index: 712