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

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

Neuron 4064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4803. Min Act: -0.0002

Data Index: 1180179 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4777. Min Act: -0.0002

Data Index: 1294191 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1217760 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4801. Min Act: -0.0002

Data Index: 142649 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4435. Min Act: -0.0001

Data Index: 1321696 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1168951 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4504. Min Act: -0.0002

Data Index: 1290867 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4210. Min Act: -0.0002

Data Index: 823053 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4270. Min Act: -0.0001

Data Index: 877451 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4213. Min Act: -0.0002

Data Index: 290220 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1080316 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4267. Min Act: -0.0001

Data Index: 179231 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4227. Min Act: -0.0002

Data Index: 1027255 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4016. Min Act: -0.0002

Data Index: 1265579 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4143. Min Act: -0.0002

Data Index: 822968 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4216. Min Act: -0.0001

Data Index: 649819 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4108. Min Act: -0.0001

Data Index: 136976 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4034. Min Act: -0.0002

Data Index: 70849 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4044. Min Act: -0.0002

Data Index: 848031 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.4803. Min Range: -0.4803

Max Act: 0.4097. Min Act: -0.0002

Data Index: 269790 (C4 (Web Text))

Max Activating Token Index: 581