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

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

Neuron 1231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2843. Min Act: -0.0000

Data Index: 14941 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1112248 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2748. Min Act: -0.0000

Data Index: 792797 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2643. Min Act: -0.0000

Data Index: 264355 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1068155 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2510. Min Act: -0.0000

Data Index: 525742 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1261581 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1298542 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2205. Min Act: -0.0000

Data Index: 151409 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2235. Min Act: -0.0000

Data Index: 49994 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2277. Min Act: -0.0000

Data Index: 877931 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2149. Min Act: -0.0000

Data Index: 669806 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2302. Min Act: -0.0001

Data Index: 688504 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2186. Min Act: -0.0000

Data Index: 859253 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2118. Min Act: -0.0001

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2143. Min Act: -0.0000

Data Index: 122482 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2032. Min Act: -0.0000

Data Index: 50998 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2156. Min Act: -0.0000

Data Index: 980207 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2067. Min Act: -0.0000

Data Index: 55737 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2156. Min Act: -0.0000

Data Index: 680706 (C4 (Web Text))

Max Activating Token Index: 251