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

Dataset: The Pile

Neuron 2388 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: 1.2377. Min Range: -1.2377

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1774361 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1834072 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1810239 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1592. Min Act: -0.0000

Data Index: 723374 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1309. Min Act: -0.0000

Data Index: 349778 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1792095 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9771. Min Act: -0.0000

Data Index: 652330 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0855. Min Act: -0.0000

Data Index: 435854 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1017993 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1590261 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9455. Min Act: -0.0000

Data Index: 521192 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9083. Min Act: -0.0000

Data Index: 200712 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1277900 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8177. Min Act: -0.0000

Data Index: 967094 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1952938 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8179. Min Act: -0.0000

Data Index: 362340 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1626024 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1981889 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1867698 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9228. Min Act: -0.0000

Data Index: 129040 (The Pile)

Max Activating Token Index: 1008