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

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

Neuron 3671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.1399. Min Act: -0.0000

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.0893. Min Act: -0.0000

Data Index: 461439 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.0783. Min Act: -0.0000

Data Index: 559369 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.2061. Min Act: -0.0000

Data Index: 501791 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.3491. Min Act: -0.0000

Data Index: 763573 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.0523. Min Act: -0.0000

Data Index: 375555 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.6370. Min Act: -0.0001

Data Index: 474532 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.7201. Min Act: -0.0000

Data Index: 179552 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.8509. Min Act: -0.0000

Data Index: 218527 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.7960. Min Act: -0.0000

Data Index: 119660 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 4.3491. Min Range: -4.3491

Max Act: 4.1082. Min Act: -0.0000

Data Index: 813281 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.5549. Min Act: -0.0000

Data Index: 411117 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.6481. Min Act: -0.0000

Data Index: 617949 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.6600. Min Act: -0.0000

Data Index: 966358 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.8123. Min Act: -0.0000

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.5100. Min Act: -0.0000

Data Index: 671042 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.6074. Min Act: -0.0000

Data Index: 1256617 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.5744. Min Act: -0.0001

Data Index: 658335 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.4363. Min Act: -0.0000

Data Index: 802889 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 4.3491. Min Range: -4.3491

Max Act: 3.5649. Min Act: -0.0000

Data Index: 1296909 (C4 (Web Text))

Max Activating Token Index: 634