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

Dataset: The Pile

Neuron 206 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0312. Min Range: -1.0312

Max Act: 1.0312. Min Act: -0.0000

Data Index: 321346 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1857385 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.9149. Min Act: 0.0000

Data Index: 256956 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8964. Min Act: -0.0000

Data Index: 938638 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8480. Min Act: -0.0000

Data Index: 155888 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8279. Min Act: -0.0000

Data Index: 591952 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7886. Min Act: -0.0000

Data Index: 574037 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7809. Min Act: -0.0000

Data Index: 809232 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7366. Min Act: -0.0000

Data Index: 106251 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1710757 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1733694 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1322190 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6016. Min Act: 0.0000

Data Index: 10246 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1703711 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1975701 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7220. Min Act: -0.0000

Data Index: 115835 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1781845 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1699181 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1035421 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1677426 (The Pile)

Max Activating Token Index: 566