Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0475. Min Act: -0.0001

Data Index: 960275 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1135113 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0424. Min Act: -0.0000

Data Index: 394627 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0421. Min Act: -0.0000

Data Index: 169679 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0435. Min Act: -0.0000

Data Index: 444877 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1356868 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0410. Min Act: -0.0000

Data Index: 587939 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0421. Min Act: -0.0000

Data Index: 486628 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0421. Min Act: -0.0000

Data Index: 931879 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1612526 (Python Code)

Max Activating Token Index: 554

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0396. Min Act: -0.0000

Data Index: 694249 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0382. Min Act: -0.0000

Data Index: 352325 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0425. Min Act: -0.0000

Data Index: 412510 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0353. Min Act: -0.0000

Data Index: 580474 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0394. Min Act: -0.0000

Data Index: 586044 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0367. Min Act: -0.0000

Data Index: 93117 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1036690 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0386. Min Act: -0.0001

Data Index: 735482 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0381. Min Act: -0.0000

Data Index: 895676 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1221018 (C4 (Web Text))

Max Activating Token Index: 234