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

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

Neuron 520 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: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0001

Data Index: 282680 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0787. Min Act: -0.0001

Data Index: 506977 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1271796 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0738. Min Act: -0.0001

Data Index: 481757 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0824. Min Act: -0.0001

Data Index: 941076 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0785. Min Act: -0.0001

Data Index: 106351 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0780. Min Act: -0.0002

Data Index: 512210 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0778. Min Act: -0.0002

Data Index: 980141 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1123859 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1182136 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0726. Min Act: -0.0001

Data Index: 48045 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0750. Min Act: -0.0001

Data Index: 419131 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0751. Min Act: -0.0001

Data Index: 112878 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1222749 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0665. Min Act: -0.0001

Data Index: 37565 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0713. Min Act: -0.0001

Data Index: 28801 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0818. Min Act: -0.0002

Data Index: 796189 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0803. Min Act: -0.0001

Data Index: 959430 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0731. Min Act: -0.0001

Data Index: 353033 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1290813 (C4 (Web Text))

Max Activating Token Index: 21