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

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

Neuron 2192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0003

Data Index: 254690 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0932. Min Act: -0.0003

Data Index: 184964 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0921. Min Act: -0.0003

Data Index: 301519 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0918. Min Act: -0.0003

Data Index: 254253 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0828. Min Act: -0.0003

Data Index: 826910 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0753. Min Act: -0.0003

Data Index: 988983 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0761. Min Act: -0.0003

Data Index: 292994 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0726. Min Act: -0.0003

Data Index: 59664 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1218712 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0722. Min Act: -0.0003

Data Index: 551059 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0732. Min Act: -0.0003

Data Index: 243543 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0685. Min Act: -0.0003

Data Index: 533177 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0673. Min Act: -0.0003

Data Index: 844877 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0681. Min Act: -0.0003

Data Index: 366207 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0640. Min Act: -0.0003

Data Index: 851178 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1091240 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0591. Min Act: -0.0003

Data Index: 526116 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1057383 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0664. Min Act: -0.0003

Data Index: 588244 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0686. Min Act: -0.0003

Data Index: 932087 (C4 (Web Text))

Max Activating Token Index: 497