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

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

Neuron 1066 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: 0.0536. Min Range: -0.0536

Max Act: 0.0514. Min Act: -0.0005

Data Index: 1257575 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0005

Data Index: 1134837 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0436. Min Act: -0.0005

Data Index: 133111 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0434. Min Act: -0.0005

Data Index: 1359433 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1163373 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0421. Min Act: -0.0005

Data Index: 505737 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0425. Min Act: -0.0005

Data Index: 344981 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0430. Min Act: -0.0005

Data Index: 1308412 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0431. Min Act: -0.0005

Data Index: 1054011 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0427. Min Act: -0.0005

Data Index: 556801 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0428. Min Act: -0.0005

Data Index: 393442 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0438. Min Act: -0.0005

Data Index: 535787 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0425. Min Act: -0.0005

Data Index: 84416 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0399. Min Act: -0.0005

Data Index: 693550 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0410. Min Act: -0.0005

Data Index: 1031942 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0423. Min Act: -0.0005

Data Index: 227720 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1080519 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0385. Min Act: -0.0005

Data Index: 632511 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0406. Min Act: -0.0005

Data Index: 60238 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0406. Min Act: -0.0005

Data Index: 500314 (C4 (Web Text))

Max Activating Token Index: 12