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

Dataset: The Pile

Neuron 2364 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: 1.6029. Min Range: -1.6029

Max Act: 1.6029. Min Act: -0.0000

Data Index: 806962 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2515. Min Act: -0.0000

Data Index: 916490 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1312866 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1756. Min Act: -0.0000

Data Index: 1602746 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1620. Min Act: -0.0000

Data Index: 844204 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1476. Min Act: -0.0000

Data Index: 343376 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0747. Min Act: -0.0000

Data Index: 766793 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1024430 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9965. Min Act: -0.0000

Data Index: 145136 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1586927 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9243. Min Act: -0.0000

Data Index: 375926 (The Pile)

Max Activating Token Index: 950

Text #11

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9801. Min Act: -0.0000

Data Index: 595667 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1133925 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9232. Min Act: -0.0000

Data Index: 290393 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.8591. Min Act: -0.0000

Data Index: 756977 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9072. Min Act: -0.0000

Data Index: 417456 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.7948. Min Act: -0.0000

Data Index: 372532 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1215533 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1060818 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1937318 (The Pile)

Max Activating Token Index: 231