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

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

Neuron 4045 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9952. Min Range: -4.9952

Max Act: 4.9952. Min Act: -0.0001

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.9617. Min Act: -0.0001

Data Index: 900854 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.8426. Min Act: -0.0001

Data Index: 754706 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.6355. Min Act: -0.0001

Data Index: 1114299 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.6086. Min Act: -0.0001

Data Index: 237242 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.5280. Min Act: -0.0001

Data Index: 748892 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.2804. Min Act: -0.0001

Data Index: 422660 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.1905. Min Act: -0.0001

Data Index: 1208013 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.9989. Min Act: -0.0001

Data Index: 503511 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.1449. Min Act: -0.0001

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.9392. Min Act: -0.0001

Data Index: 286015 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.0651. Min Act: -0.0001

Data Index: 360844 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 4.9952. Min Range: -4.9952

Max Act: 3.0732. Min Act: -0.0001

Data Index: 1324551 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.8370. Min Act: -0.0001

Data Index: 362544 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.6761. Min Act: -0.0001

Data Index: 19826 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.6626. Min Act: -0.0001

Data Index: 119908 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.5520. Min Act: -0.0001

Data Index: 36994 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.7126. Min Act: -0.0001

Data Index: 1260939 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.6620. Min Act: -0.0001

Data Index: 327860 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 4.9952. Min Range: -4.9952

Max Act: 2.3784. Min Act: -0.0001

Data Index: 524720 (C4 (Web Text))

Max Activating Token Index: 20