Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 982 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6641. Min Act: -0.0002

Data Index: 40098 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6028. Min Act: -0.0002

Data Index: 316404 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5592. Min Act: -0.0002

Data Index: 140680 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5220. Min Act: -0.0002

Data Index: 1013912 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5313. Min Act: -0.0002

Data Index: 381393 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5277. Min Act: -0.0002

Data Index: 217740 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5125. Min Act: -0.0002

Data Index: 1071329 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5077. Min Act: -0.0002

Data Index: 680347 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5299. Min Act: -0.0002

Data Index: 1090621 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4799. Min Act: -0.0002

Data Index: 860459 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4952. Min Act: -0.0002

Data Index: 9431 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5071. Min Act: -0.0002

Data Index: 314068 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5008. Min Act: -0.0002

Data Index: 480582 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5171. Min Act: -0.0002

Data Index: 290584 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4791. Min Act: -0.0002

Data Index: 954989 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5121. Min Act: -0.0002

Data Index: 457832 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4961. Min Act: -0.0002

Data Index: 1206215 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5075. Min Act: -0.0002

Data Index: 694324 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4704. Min Act: -0.0002

Data Index: 201353 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4676. Min Act: -0.0002

Data Index: 624870 (C4 (Web Text))

Max Activating Token Index: 981