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

Dataset: The Pile

Neuron 2972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.1610. Min Act: -0.0000

Data Index: 560035 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.1610. Min Range: -1.1610

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1371223 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1786814 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8736. Min Act: -0.0000

Data Index: 794228 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9001. Min Act: -0.0000

Data Index: 293755 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1135637 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8287. Min Act: -0.0000

Data Index: 358844 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1774073 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8706. Min Act: -0.0000

Data Index: 408599 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1914487 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1623465 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1551614 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1522259 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1331523 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7951. Min Act: -0.0000

Data Index: 387987 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.6179. Min Act: -0.0000

Data Index: 421421 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7823. Min Act: -0.0000

Data Index: 772964 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7522. Min Act: -0.0000

Data Index: 690286 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7779. Min Act: -0.0000

Data Index: 91251 (The Pile)

Max Activating Token Index: 851