Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3052 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1256946 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1337009 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1494. Min Act: -0.0000

Data Index: 896452 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0410. Min Act: -0.0000

Data Index: 664844 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0151. Min Act: -0.0000

Data Index: 132085 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1910071 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1051499 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9904. Min Act: -0.0000

Data Index: 200625 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1619815 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1175432 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9144. Min Act: -0.0000

Data Index: 609521 (The Pile)

Max Activating Token Index: 697

Text #11

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1453799 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0226. Min Act: -0.0000

Data Index: 674285 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9576. Min Act: -0.0000

Data Index: 258296 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9902. Min Act: -0.0000

Data Index: 591301 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0100. Min Act: -0.0000

Data Index: 764019 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1724673 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1904814 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0099. Min Act: -0.0000

Data Index: 754016 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9352. Min Act: -0.0000

Data Index: 914563 (The Pile)

Max Activating Token Index: 866