Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1128 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0410. Min Act: -0.0006

Data Index: 876571 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1350169 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0006

Data Index: 13182 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0398. Min Act: -0.0006

Data Index: 171850 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1019624 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0381. Min Act: -0.0006

Data Index: 241346 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1316938 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0381. Min Act: -0.0006

Data Index: 307301 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1347191 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1122929 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0372. Min Act: -0.0006

Data Index: 939524 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0371. Min Act: -0.0006

Data Index: 250172 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0379. Min Act: -0.0006

Data Index: 971461 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0369. Min Act: -0.0006

Data Index: 185540 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0367. Min Act: -0.0006

Data Index: 484116 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0384. Min Act: -0.0006

Data Index: 243595 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0367. Min Act: -0.0006

Data Index: 576245 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1142270 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0364. Min Act: -0.0006

Data Index: 351921 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0352. Min Act: -0.0006

Data Index: 844364 (C4 (Web Text))

Max Activating Token Index: 484