Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0330. Min Range: -1.0330

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1077744 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.8527. Min Act: 0.0000

Data Index: 404254 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.7872. Min Act: -0.0000

Data Index: 657960 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.8927. Min Act: -0.0000

Data Index: 391594 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.8059. Min Act: 0.0000

Data Index: 844635 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.6732. Min Act: -0.0000

Data Index: 780461 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.6856. Min Act: 0.0000

Data Index: 1129558 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.6434. Min Act: 0.0001

Data Index: 60283 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.6183. Min Act: -0.0000

Data Index: 660056 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1275565 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.6289. Min Act: -0.0000

Data Index: 990622 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5823. Min Act: -0.0000

Data Index: 849212 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5531. Min Act: -0.0000

Data Index: 793765 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5464. Min Act: -0.0000

Data Index: 199647 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5529. Min Act: -0.0000

Data Index: 333982 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1133815 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5376. Min Act: -0.0000

Data Index: 462458 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5459. Min Act: 0.0001

Data Index: 1129957 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5766. Min Act: -0.0000

Data Index: 836603 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.0330. Min Range: -1.0330

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1147802 (C4 (Web Text))

Max Activating Token Index: 896