Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3020 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.9771. Min Act: -0.0002

Data Index: 357532 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.9367. Min Act: -0.0002

Data Index: 1110111 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.9381. Min Act: -0.0002

Data Index: 45212 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8984. Min Act: -0.0002

Data Index: 716429 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8933. Min Act: -0.0002

Data Index: 685302 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8554. Min Act: -0.0002

Data Index: 1004201 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8602. Min Act: -0.0002

Data Index: 203881 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8353. Min Act: -0.0002

Data Index: 589130 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8230. Min Act: -0.0002

Data Index: 1193292 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8243. Min Act: -0.0002

Data Index: 1080618 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8411. Min Act: -0.0002

Data Index: 1226229 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8247. Min Act: -0.0002

Data Index: 104358 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8303. Min Act: -0.0002

Data Index: 218863 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8300. Min Act: -0.0002

Data Index: 446481 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8207. Min Act: -0.0002

Data Index: 103614 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8232. Min Act: -0.0002

Data Index: 727732 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8203. Min Act: -0.0002

Data Index: 1004181 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8092. Min Act: -0.0002

Data Index: 1169687 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8010. Min Act: -0.0002

Data Index: 229408 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.9771. Min Range: -0.9771

Max Act: 0.8099. Min Act: -0.0002

Data Index: 702474 (C4 (Web Text))

Max Activating Token Index: 171