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

Dataset: The Pile

Neuron 3371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0440. Min Range: -3.0440

Max Act: 3.0440. Min Act: -0.0000

Data Index: 1469186 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.3666. Min Act: -0.0000

Data Index: 977899 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1991297 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.3244. Min Act: -0.0000

Data Index: 456162 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.1663. Min Act: -0.0000

Data Index: 553326 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.0018. Min Act: -0.0000

Data Index: 398616 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.0624. Min Act: -0.0000

Data Index: 717328 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.1375. Min Act: -0.0000

Data Index: 339529 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.0940. Min Act: -0.0000

Data Index: 496474 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.8405. Min Act: -0.0000

Data Index: 914530 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1890263 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 3.0440. Min Range: -3.0440

Max Act: 2.0077. Min Act: -0.0000

Data Index: 24031 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.8728. Min Act: -0.0000

Data Index: 102894 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.7622. Min Act: -0.0000

Data Index: 1596542 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.8608. Min Act: -0.0000

Data Index: 1967565 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1934910 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.7603. Min Act: -0.0000

Data Index: 158129 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.8024. Min Act: -0.0000

Data Index: 1275405 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.7129. Min Act: -0.0000

Data Index: 1574181 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 3.0440. Min Range: -3.0440

Max Act: 1.8055. Min Act: -0.0000

Data Index: 491179 (The Pile)

Max Activating Token Index: 446