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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.7889. Min Act: -0.0001

Data Index: 432611 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6119. Min Act: -0.0001

Data Index: 785104 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6690. Min Act: -0.0000

Data Index: 959113 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1263045 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6390. Min Act: -0.0001

Data Index: 774346 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6089. Min Act: -0.0001

Data Index: 201271 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6040. Min Act: -0.0001

Data Index: 1032003 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1358445 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1076054 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1178298 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1084640 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5546. Min Act: -0.0000

Data Index: 182121 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5541. Min Act: -0.0000

Data Index: 16525 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5529. Min Act: -0.0000

Data Index: 637469 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1272501 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5636. Min Act: -0.0000

Data Index: 551609 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5052. Min Act: -0.0001

Data Index: 715045 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5372. Min Act: -0.0000

Data Index: 735125 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5647. Min Act: -0.0000

Data Index: 232725 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1178798 (C4 (Web Text))

Max Activating Token Index: 530