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

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

Neuron 3943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0001

Data Index: 890598 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1038386 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0991. Min Act: -0.0001

Data Index: 720565 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1275109 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0920. Min Act: -0.0001

Data Index: 475432 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0803. Min Act: -0.0001

Data Index: 561161 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0877. Min Act: -0.0001

Data Index: 638961 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0907. Min Act: -0.0001

Data Index: 390539 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0836. Min Act: -0.0001

Data Index: 719173 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0831. Min Act: -0.0001

Data Index: 419744 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0827. Min Act: -0.0001

Data Index: 680753 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1236954 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0787. Min Act: -0.0001

Data Index: 899686 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0867. Min Act: -0.0001

Data Index: 509088 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0863. Min Act: -0.0001

Data Index: 336838 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0771. Min Act: -0.0000

Data Index: 235313 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1203126 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0749. Min Act: -0.0001

Data Index: 718334 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0745. Min Act: -0.0001

Data Index: 270473 (C4 (Web Text))

Max Activating Token Index: 411