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

Dataset: The Pile

Neuron 1466 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1320541 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9942. Min Act: -0.0000

Data Index: 689002 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8867. Min Act: -0.0000

Data Index: 391882 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8404. Min Act: -0.0000

Data Index: 747220 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9166. Min Act: -0.0000

Data Index: 975901 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8862. Min Act: -0.0000

Data Index: 891362 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9043. Min Act: -0.0000

Data Index: 628664 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8221. Min Act: -0.0000

Data Index: 995539 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8390. Min Act: -0.0000

Data Index: 626368 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7873. Min Act: -0.0000

Data Index: 965620 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7865. Min Act: -0.0000

Data Index: 590197 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9107. Min Act: -0.0000

Data Index: 916761 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8010. Min Act: -0.0000

Data Index: 497210 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8331. Min Act: -0.0000

Data Index: 179990 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7221. Min Act: -0.0000

Data Index: 249962 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1241656 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.6853. Min Act: -0.0000

Data Index: 131686 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7601. Min Act: -0.0000

Data Index: 512716 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1828690 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1253024 (The Pile)

Max Activating Token Index: 312