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

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

Neuron 4400 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.2135. Min Act: -0.0000

Data Index: 1327283 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.3494. Min Act: -0.0000

Data Index: 187463 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.1829. Min Act: -0.0000

Data Index: 292542 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.9282. Min Act: -0.0000

Data Index: 1206001 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.7673. Min Act: -0.0000

Data Index: 281022 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.8971. Min Act: -0.0000

Data Index: 707388 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.8836. Min Act: -0.0000

Data Index: 330956 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 3.3494. Min Range: -3.3494

Max Act: 3.0286. Min Act: -0.0000

Data Index: 468346 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.7163. Min Act: -0.0000

Data Index: 1338312 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.8533. Min Act: -0.0000

Data Index: 665788 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.9481. Min Act: -0.0000

Data Index: 174195 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.8020. Min Act: -0.0000

Data Index: 510698 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.9366. Min Act: -0.0000

Data Index: 134443 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.7628. Min Act: -0.0000

Data Index: 390631 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.4988. Min Act: -0.0000

Data Index: 653862 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.7568. Min Act: -0.0000

Data Index: 831300 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.5251. Min Act: -0.0000

Data Index: 294089 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.6412. Min Act: -0.0000

Data Index: 419212 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.6336. Min Act: -0.0000

Data Index: 21879 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 3.3494. Min Range: -3.3494

Max Act: 2.3588. Min Act: -0.0000

Data Index: 298914 (C4 (Web Text))

Max Activating Token Index: 605