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

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

Neuron 857 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0002

Data Index: 410910 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1191963 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0435. Min Act: -0.0002

Data Index: 447387 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0410. Min Act: -0.0002

Data Index: 845292 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1093899 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0405. Min Act: -0.0002

Data Index: 893007 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1069678 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0390. Min Act: -0.0002

Data Index: 59879 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0417. Min Act: -0.0002

Data Index: 493731 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0405. Min Act: -0.0002

Data Index: 535789 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0417. Min Act: -0.0002

Data Index: 66630 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0410. Min Act: -0.0002

Data Index: 504691 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0400. Min Act: -0.0002

Data Index: 33266 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0402. Min Act: -0.0002

Data Index: 902254 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1264902 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0413. Min Act: -0.0002

Data Index: 797621 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0393. Min Act: -0.0002

Data Index: 873253 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1120268 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0398. Min Act: -0.0002

Data Index: 480933 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0397. Min Act: -0.0002

Data Index: 877663 (C4 (Web Text))

Max Activating Token Index: 317