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

Dataset: The Pile

Neuron 1709 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: 1.3956. Min Range: -1.3956

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1057338 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2551. Min Act: -0.0000

Data Index: 939128 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2309. Min Act: -0.0000

Data Index: 182586 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.2134. Min Act: -0.0000

Data Index: 409648 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0974. Min Act: -0.0000

Data Index: 219645 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1887628 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.1431. Min Act: -0.0000

Data Index: 184053 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.1053. Min Act: -0.0000

Data Index: 505706 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.1363. Min Act: -0.0000

Data Index: 218172 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9899. Min Act: -0.0000

Data Index: 390113 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1550650 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0375. Min Act: -0.0000

Data Index: 290006 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9757. Min Act: 0.0000

Data Index: 1374172 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9681. Min Act: -0.0000

Data Index: 835772 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0838. Min Act: -0.0000

Data Index: 800233 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.0208. Min Act: -0.0000

Data Index: 174339 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1897923 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 1.3956. Min Range: -1.3956

Max Act: 1.1729. Min Act: 0.0000

Data Index: 673407 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9230. Min Act: -0.0000

Data Index: 344682 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 1.3956. Min Range: -1.3956

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1423432 (The Pile)

Max Activating Token Index: 481