Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1074 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8559. Min Range: -2.8559

Max Act: 2.8559. Min Act: -0.0000

Data Index: 699203 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 2.8559. Min Range: -2.8559

Max Act: 2.1492. Min Act: -0.0000

Data Index: 160422 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.8377. Min Act: -0.0000

Data Index: 788915 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1017316 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.7903. Min Act: -0.0000

Data Index: 1148074 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.7834. Min Act: -0.0000

Data Index: 453263 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.7503. Min Act: -0.0000

Data Index: 1119073 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.7536. Min Act: -0.0000

Data Index: 831312 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.6269. Min Act: -0.0000

Data Index: 150803 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.5613. Min Act: -0.0000

Data Index: 846236 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.7267. Min Act: -0.0000

Data Index: 1114904 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.6120. Min Act: -0.0000

Data Index: 872894 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.6017. Min Act: -0.0000

Data Index: 675623 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.5829. Min Act: -0.0000

Data Index: 330785 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.6351. Min Act: -0.0000

Data Index: 186464 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1304798 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.4289. Min Act: -0.0000

Data Index: 50712 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.3117. Min Act: -0.0000

Data Index: 799004 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.3042. Min Act: -0.0000

Data Index: 1320557 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 2.8559. Min Range: -2.8559

Max Act: 1.3864. Min Act: -0.0000

Data Index: 391068 (C4 (Web Text))

Max Activating Token Index: 951