Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1357 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2983. Min Act: -0.0001

Data Index: 1233893 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2873. Min Act: -0.0001

Data Index: 877051 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.3008. Min Act: -0.0001

Data Index: 698257 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2689. Min Act: -0.0001

Data Index: 579226 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2416. Min Act: -0.0001

Data Index: 427183 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2343. Min Act: -0.0001

Data Index: 397902 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2310. Min Act: -0.0001

Data Index: 172837 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2231. Min Act: -0.0001

Data Index: 325804 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2100. Min Act: -0.0001

Data Index: 144669 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2169. Min Act: -0.0000

Data Index: 749883 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2165. Min Act: -0.0001

Data Index: 969631 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2113. Min Act: -0.0001

Data Index: 579893 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2184. Min Act: -0.0001

Data Index: 445967 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2167. Min Act: -0.0001

Data Index: 943933 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1226627 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2006. Min Act: -0.0001

Data Index: 384094 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.1955. Min Act: -0.0001

Data Index: 924495 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2048. Min Act: -0.0001

Data Index: 406619 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1325011 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2045. Min Act: -0.0000

Data Index: 876289 (C4 (Web Text))

Max Activating Token Index: 335