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

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

Neuron 1439 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0005

Data Index: 639918 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0490. Min Act: -0.0005

Data Index: 781236 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0450. Min Act: -0.0005

Data Index: 236019 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0451. Min Act: -0.0005

Data Index: 640162 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0439. Min Act: -0.0005

Data Index: 296187 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0449. Min Act: -0.0005

Data Index: 42334 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0434. Min Act: -0.0005

Data Index: 381649 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0431. Min Act: -0.0005

Data Index: 680699 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0438. Min Act: -0.0005

Data Index: 740264 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0424. Min Act: -0.0005

Data Index: 551442 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0428. Min Act: -0.0005

Data Index: 96483 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0426. Min Act: -0.0005

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0407. Min Act: -0.0005

Data Index: 584339 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0429. Min Act: -0.0005

Data Index: 192076 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0423. Min Act: -0.0005

Data Index: 1359580 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1317684 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0397. Min Act: -0.0005

Data Index: 274184 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0404. Min Act: -0.0005

Data Index: 1127981 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0400. Min Act: -0.0005

Data Index: 937567 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0392. Min Act: -0.0005

Data Index: 899004 (C4 (Web Text))

Max Activating Token Index: 722