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

Dataset: The Pile

Neuron 2093 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1947648 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.2230. Min Act: -0.0000

Data Index: 340421 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.1833. Min Act: -0.0000

Data Index: 427462 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.1607. Min Act: -0.0000

Data Index: 668280 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.2043. Min Act: -0.0000

Data Index: 796599 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1520517 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0703. Min Act: -0.0000

Data Index: 1396424 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0853. Min Act: -0.0000

Data Index: 363531 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9990. Min Act: -0.0000

Data Index: 978551 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1803921 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0054. Min Act: -0.0000

Data Index: 791244 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9741. Min Act: -0.0000

Data Index: 390870 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1182617 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1038262 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9299. Min Act: -0.0000

Data Index: 818864 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1492115 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9219. Min Act: -0.0000

Data Index: 425491 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9171. Min Act: -0.0000

Data Index: 136545 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9478. Min Act: -0.0000

Data Index: 683459 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1213937 (The Pile)

Max Activating Token Index: 463