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

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

Neuron 667 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.7492. Min Act: -0.0001

Data Index: 611443 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.7568. Min Act: -0.0001

Data Index: 168593 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.5401. Min Act: -0.0001

Data Index: 679314 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6103. Min Act: -0.0001

Data Index: 42521 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6154. Min Act: -0.0001

Data Index: 1187640 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.6247. Min Act: -0.0001

Data Index: 262755 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.5662. Min Act: -0.0001

Data Index: 918580 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4077. Min Act: -0.0001

Data Index: 344203 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.5125. Min Act: -0.0001

Data Index: 382974 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4151. Min Act: -0.0001

Data Index: 37930 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4888. Min Act: -0.0001

Data Index: 623338 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3683. Min Act: -0.0001

Data Index: 1048447 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3854. Min Act: -0.0001

Data Index: 515393 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.4246. Min Act: -0.0001

Data Index: 799019 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3805. Min Act: -0.0001

Data Index: 1230538 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.0970. Min Act: -0.0001

Data Index: 745720 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3482. Min Act: -0.0001

Data Index: 797677 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3034. Min Act: -0.0001

Data Index: 213231 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3370. Min Act: -0.0001

Data Index: 1052091 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.7568. Min Range: -1.7568

Max Act: 1.3315. Min Act: -0.0001

Data Index: 59889 (C4 (Web Text))

Max Activating Token Index: 78