Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 114 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5591. Min Act: -0.0001

Data Index: 1049843 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4900. Min Act: -0.0001

Data Index: 662241 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4227. Min Act: -0.0001

Data Index: 804516 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3867. Min Act: -0.0001

Data Index: 526871 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4092. Min Act: -0.0001

Data Index: 943865 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3779. Min Act: -0.0001

Data Index: 581018 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4198. Min Act: -0.0001

Data Index: 550689 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4286. Min Act: -0.0001

Data Index: 23491 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4031. Min Act: -0.0001

Data Index: 551657 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4187. Min Act: -0.0001

Data Index: 189150 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4023. Min Act: -0.0001

Data Index: 452816 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4136. Min Act: -0.0001

Data Index: 28641 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4134. Min Act: -0.0001

Data Index: 212486 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4050. Min Act: -0.0001

Data Index: 1002992 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4175. Min Act: -0.0001

Data Index: 360745 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4084. Min Act: -0.0001

Data Index: 721393 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3937. Min Act: -0.0001

Data Index: 802432 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4051. Min Act: -0.0001

Data Index: 700329 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4017. Min Act: -0.0001

Data Index: 494914 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4334. Min Act: -0.0001

Data Index: 1179689 (C4 (Web Text))

Max Activating Token Index: 284