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

Dataset: The Pile

Neuron 4981 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: 1.0264. Min Range: -1.0264

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1822695 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8573. Min Act: -0.0000

Data Index: 316604 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8772. Min Act: -0.0000

Data Index: 428110 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7605. Min Act: -0.0000

Data Index: 861404 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1463490 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8069. Min Act: -0.0000

Data Index: 433709 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1808383 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8202. Min Act: -0.0000

Data Index: 145207 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7478. Min Act: -0.0000

Data Index: 194930 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8543. Min Act: -0.0000

Data Index: 132089 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7049. Min Act: -0.0000

Data Index: 991304 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1398733 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1400533 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1741802 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.6839. Min Act: -0.0000

Data Index: 669565 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1788174 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8159. Min Act: -0.0000

Data Index: 81169 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1937688 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7282. Min Act: -0.0000

Data Index: 116814 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.6746. Min Act: -0.0000

Data Index: 371823 (The Pile)

Max Activating Token Index: 270