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

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

Neuron 2449 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.5243. Min Act: -0.0000

Data Index: 60300 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4722. Min Act: -0.0000

Data Index: 130141 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1047706 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4418. Min Act: -0.0000

Data Index: 106203 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4063. Min Act: -0.0000

Data Index: 505731 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4205. Min Act: -0.0000

Data Index: 550907 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4072. Min Act: -0.0000

Data Index: 785486 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4109. Min Act: 0.0000

Data Index: 934565 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4068. Min Act: -0.0000

Data Index: 599684 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4060. Min Act: -0.0000

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.4213. Min Act: -0.0000

Data Index: 639048 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1118279 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1085103 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3937. Min Act: -0.0000

Data Index: 682975 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3874. Min Act: 0.0000

Data Index: 291887 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1280533 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3631. Min Act: 0.0000

Data Index: 823195 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3742. Min Act: -0.0000

Data Index: 777046 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3626. Min Act: -0.0000

Data Index: 281319 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.5243. Min Range: -0.5243

Max Act: 0.3680. Min Act: -0.0000

Data Index: 815199 (C4 (Web Text))

Max Activating Token Index: 866