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

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

Neuron 242 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3623. Min Act: -0.0005

Data Index: 1140662 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3150. Min Act: -0.0005

Data Index: 486967 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3382. Min Act: -0.0005

Data Index: 287478 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3444. Min Act: -0.0005

Data Index: 619870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3352. Min Act: -0.0005

Data Index: 996347 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3309. Min Act: -0.0005

Data Index: 978187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3128. Min Act: -0.0005

Data Index: 463456 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3235. Min Act: -0.0005

Data Index: 368586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3220. Min Act: -0.0005

Data Index: 262334 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3198. Min Act: -0.0005

Data Index: 567708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3053. Min Act: -0.0005

Data Index: 1355156 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3229. Min Act: -0.0005

Data Index: 833231 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3213. Min Act: -0.0005

Data Index: 1090653 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3082. Min Act: -0.0005

Data Index: 1160821 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2955. Min Act: -0.0005

Data Index: 1297355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3056. Min Act: -0.0005

Data Index: 1335122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2898. Min Act: -0.0005

Data Index: 1206558 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2987. Min Act: -0.0005

Data Index: 1283781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2971. Min Act: -0.0005

Data Index: 2535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2951. Min Act: -0.0005

Data Index: 204166 (C4 (Web Text))

Max Activating Token Index: 1023