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

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

Neuron 2057 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0004

Data Index: 333669 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1048. Min Act: -0.0004

Data Index: 1307856 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1022. Min Act: -0.0004

Data Index: 175179 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0982. Min Act: -0.0004

Data Index: 257256 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1008. Min Act: -0.0004

Data Index: 1074647 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0922. Min Act: -0.0004

Data Index: 468821 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0903. Min Act: -0.0004

Data Index: 461849 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0939. Min Act: -0.0004

Data Index: 1107542 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0870. Min Act: -0.0004

Data Index: 1337587 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0926. Min Act: -0.0004

Data Index: 467694 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0893. Min Act: -0.0004

Data Index: 589004 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0886. Min Act: -0.0004

Data Index: 996599 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0875. Min Act: -0.0004

Data Index: 1271077 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0870. Min Act: -0.0004

Data Index: 465953 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0857. Min Act: -0.0004

Data Index: 505346 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0849. Min Act: -0.0004

Data Index: 789051 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0882. Min Act: -0.0004

Data Index: 180008 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0813. Min Act: -0.0004

Data Index: 69109 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0831. Min Act: -0.0004

Data Index: 742328 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0835. Min Act: -0.0004

Data Index: 1288468 (C4 (Web Text))

Max Activating Token Index: 469