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

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

Neuron 4633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.6119. Min Act: -0.0000

Data Index: 232498 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5955. Min Act: -0.0000

Data Index: 230147 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5791. Min Act: -0.0000

Data Index: 413540 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5383. Min Act: -0.0000

Data Index: 475955 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5179. Min Act: -0.0000

Data Index: 485602 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5490. Min Act: -0.0000

Data Index: 576196 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5035. Min Act: -0.0000

Data Index: 613511 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5129. Min Act: -0.0000

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4977. Min Act: -0.0000

Data Index: 838156 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4562. Min Act: -0.0000

Data Index: 34163 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4833. Min Act: -0.0000

Data Index: 414822 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1103983 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4226. Min Act: -0.0000

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4458. Min Act: -0.0000

Data Index: 821018 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3990. Min Act: -0.0000

Data Index: 701693 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4145. Min Act: -0.0000

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4081. Min Act: -0.0000

Data Index: 491153 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4167. Min Act: -0.0000

Data Index: 871027 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4296. Min Act: -0.0000

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 825