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

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

Neuron 3413 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: 3.2234. Min Range: -3.2234

Max Act: 3.2234. Min Act: -0.0002

Data Index: 1018013 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.9620. Min Act: -0.0002

Data Index: 106130 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.8930. Min Act: -0.0002

Data Index: 592898 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.8124. Min Act: -0.0002

Data Index: 431911 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.8097. Min Act: -0.0002

Data Index: 526260 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.6606. Min Act: -0.0002

Data Index: 1088805 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.6503. Min Act: -0.0002

Data Index: 570671 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.7178. Min Act: -0.0002

Data Index: 523326 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.6363. Min Act: -0.0002

Data Index: 911565 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.6205. Min Act: -0.0002

Data Index: 136064 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.5857. Min Act: -0.0002

Data Index: 251759 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.5703. Min Act: -0.0002

Data Index: 1210063 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.5617. Min Act: -0.0002

Data Index: 459462 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.4737. Min Act: -0.0002

Data Index: 775912 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.4785. Min Act: -0.0002

Data Index: 263827 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.5398. Min Act: -0.0002

Data Index: 977125 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.5621. Min Act: -0.0002

Data Index: 1232821 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.4793. Min Act: -0.0002

Data Index: 277298 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.4975. Min Act: -0.0002

Data Index: 147514 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 3.2234. Min Range: -3.2234

Max Act: 2.4289. Min Act: -0.0002

Data Index: 913030 (C4 (Web Text))

Max Activating Token Index: 282