Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2024 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.4133. Min Act: -0.0000

Data Index: 229656 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3976. Min Act: -0.0000

Data Index: 62578 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.4053. Min Act: -0.0000

Data Index: 138844 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3936. Min Act: -0.0000

Data Index: 665727 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3701. Min Act: -0.0000

Data Index: 421447 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3764. Min Act: -0.0000

Data Index: 499154 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3473. Min Act: -0.0000

Data Index: 682036 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1043398 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3219. Min Act: -0.0000

Data Index: 175888 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1135844 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3204. Min Act: -0.0000

Data Index: 877954 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2981. Min Act: -0.0000

Data Index: 295009 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3101. Min Act: -0.0000

Data Index: 637412 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3115. Min Act: -0.0000

Data Index: 980684 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1100497 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.3075. Min Act: -0.0000

Data Index: 704825 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2942. Min Act: -0.0000

Data Index: 525898 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2932. Min Act: -0.0000

Data Index: 130234 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2915. Min Act: -0.0000

Data Index: 877755 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.4133. Min Range: -0.4133

Max Act: 0.2903. Min Act: -0.0000

Data Index: 823300 (C4 (Web Text))

Max Activating Token Index: 493