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

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

Neuron 2164 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.8281. Min Act: -0.0001

Data Index: 416019 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0793. Min Act: -0.0001

Data Index: 275431 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1826. Min Act: -0.0001

Data Index: 537803 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1233. Min Act: -0.0001

Data Index: 1107800 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.2794. Min Act: -0.0001

Data Index: 1218353 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1250. Min Act: -0.0001

Data Index: 479198 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.6968. Min Act: -0.0001

Data Index: 33216 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.9410. Min Act: -0.0001

Data Index: 43011 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.8451. Min Act: -0.0001

Data Index: 1246425 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.9679. Min Act: -0.0001

Data Index: 2430 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1046. Min Act: -0.0001

Data Index: 19530 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.8143. Min Act: -0.0001

Data Index: 300206 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.8109. Min Act: -0.0001

Data Index: 394076 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.9405. Min Act: -0.0001

Data Index: 1027655 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.7916. Min Act: -0.0001

Data Index: 190100 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.9807. Min Act: -0.0001

Data Index: 813164 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.7117. Min Act: -0.0001

Data Index: 1223815 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.5781. Min Act: -0.0001

Data Index: 69357 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.8365. Min Act: -0.0001

Data Index: 315854 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.2794. Min Range: -3.2794

Max Act: 2.5852. Min Act: -0.0001

Data Index: 605761 (C4 (Web Text))

Max Activating Token Index: 631