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

Dataset: The Pile

Neuron 4570 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8199. Min Act: -0.0000

Data Index: 437354 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1360189 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1030843 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.9215. Min Act: -0.0000

Data Index: 588623 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1932351 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1855570 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1550589 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8750. Min Act: -0.0000

Data Index: 685017 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1055629 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6672. Min Act: -0.0000

Data Index: 68146 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7493. Min Act: -0.0000

Data Index: 294123 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8114. Min Act: -0.0000

Data Index: 343139 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1961794 (The Pile)

Max Activating Token Index: 700

Text #13

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7002. Min Act: -0.0000

Data Index: 570807 (The Pile)

Max Activating Token Index: 232

Text #14

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1324393 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1152279 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1783306 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.7529. Min Act: -0.0000

Data Index: 658447 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1629704 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.9215. Min Range: -0.9215

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1077992 (The Pile)

Max Activating Token Index: 858