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

Dataset: The Pile

Neuron 1896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6346. Min Act: -0.0000

Data Index: 560625 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1070087 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4597. Min Act: -0.0000

Data Index: 271792 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5309. Min Act: -0.0000

Data Index: 242885 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4177. Min Act: -0.0000

Data Index: 485943 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1173401 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3921. Min Act: -0.0001

Data Index: 313036 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1849572 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1705004 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1745331 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4208. Min Act: -0.0000

Data Index: 334056 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3503. Min Act: -0.0000

Data Index: 611722 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1270600 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3480. Min Act: -0.0000

Data Index: 71599 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3334. Min Act: -0.0000

Data Index: 389766 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3772. Min Act: -0.0000

Data Index: 904986 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1476450 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1984655 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.3425. Min Act: -0.0000

Data Index: 393258 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.2902. Min Act: -0.0000

Data Index: 283073 (The Pile)

Max Activating Token Index: 227