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

Dataset: The Pile

Neuron 2596 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1179. Min Range: -4.1179

Max Act: 4.1179. Min Act: -0.0000

Data Index: 659403 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.9676. Min Act: -0.0000

Data Index: 1426640 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 4.1179. Min Range: -4.1179

Max Act: 4.0696. Min Act: -0.0000

Data Index: 425685 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.4552. Min Act: -0.0000

Data Index: 1963983 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.0584. Min Act: -0.0000

Data Index: 1691250 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.1256. Min Act: -0.0000

Data Index: 444264 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.3466. Min Act: -0.0000

Data Index: 503183 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.2253. Min Act: -0.0000

Data Index: 1132828 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.0472. Min Act: -0.0000

Data Index: 1386652 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.0293. Min Act: -0.0000

Data Index: 1562077 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.1588. Min Act: -0.0000

Data Index: 1718321 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.0892. Min Act: -0.0000

Data Index: 438495 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 4.1179. Min Range: -4.1179

Max Act: 3.0379. Min Act: -0.0000

Data Index: 431764 (The Pile)

Max Activating Token Index: 422

Text #13

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.9006. Min Act: -0.0000

Data Index: 1294338 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.8781. Min Act: -0.0000

Data Index: 1248683 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.7212. Min Act: -0.0000

Data Index: 372603 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.7434. Min Act: -0.0000

Data Index: 1958272 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.5603. Min Act: -0.0000

Data Index: 1490555 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.7942. Min Act: -0.0000

Data Index: 1506476 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 4.1179. Min Range: -4.1179

Max Act: 2.7737. Min Act: -0.0000

Data Index: 1217076 (The Pile)

Max Activating Token Index: 458