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

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

Neuron 1864 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: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1083723 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0408. Min Act: -0.0002

Data Index: 371897 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1033941 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0377. Min Act: -0.0002

Data Index: 590417 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0364. Min Act: -0.0001

Data Index: 679020 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0354. Min Act: -0.0002

Data Index: 368986 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0356. Min Act: -0.0002

Data Index: 753217 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0345. Min Act: -0.0002

Data Index: 240874 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1287923 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0350. Min Act: -0.0002

Data Index: 883420 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1022981 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0334. Min Act: -0.0002

Data Index: 670860 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1048630 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1049678 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1029865 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0334. Min Act: -0.0002

Data Index: 802276 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1263058 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0333. Min Act: -0.0001

Data Index: 201485 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0332. Min Act: -0.0002

Data Index: 678705 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1028150 (C4 (Web Text))

Max Activating Token Index: 170