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

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

Neuron 3963 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: 0.9625. Min Range: -0.9625

Max Act: 0.8380. Min Act: -0.0000

Data Index: 508558 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.9162. Min Act: -0.0000

Data Index: 745980 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.8497. Min Act: -0.0000

Data Index: 316872 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1358212 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.9625. Min Act: -0.0000

Data Index: 391810 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7822. Min Act: -0.0000

Data Index: 552030 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7974. Min Act: -0.0000

Data Index: 649177 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7207. Min Act: -0.0000

Data Index: 431632 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1235753 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7481. Min Act: -0.0000

Data Index: 467556 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7516. Min Act: -0.0000

Data Index: 74168 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6993. Min Act: -0.0000

Data Index: 236417 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6288. Min Act: -0.0000

Data Index: 453987 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6562. Min Act: -0.0000

Data Index: 584635 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1133190 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6377. Min Act: -0.0000

Data Index: 52238 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6673. Min Act: -0.0000

Data Index: 717466 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6485. Min Act: -0.0000

Data Index: 442775 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.6152. Min Act: -0.0000

Data Index: 246794 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.9625. Min Range: -0.9625

Max Act: 0.5911. Min Act: -0.0000

Data Index: 342108 (C4 (Web Text))

Max Activating Token Index: 873