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

Dataset: The Pile

Neuron 1187 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5881. Min Act: -0.0000

Data Index: 393779 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5108. Min Act: -0.0000

Data Index: 43114 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1477937 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5040. Min Act: -0.0000

Data Index: 167559 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1719292 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4974. Min Act: -0.0000

Data Index: 365408 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4964. Min Act: -0.0000

Data Index: 405777 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1287823 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4975. Min Act: -0.0000

Data Index: 162196 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1680816 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1764600 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4860. Min Act: -0.0000

Data Index: 196171 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4476. Min Act: -0.0000

Data Index: 496040 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1431172 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1178249 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4127. Min Act: -0.0000

Data Index: 96921 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4453. Min Act: -0.0000

Data Index: 144584 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1475793 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4299. Min Act: -0.0000

Data Index: 497865 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4304. Min Act: -0.0000

Data Index: 744242 (The Pile)

Max Activating Token Index: 1011