Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 159 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.6504. Min Range: -5.6504

Max Act: 5.6504. Min Act: -0.0000

Data Index: 865172 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.9386. Min Act: -0.0000

Data Index: 1036375 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.9943. Min Act: -0.0000

Data Index: 1329631 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.8164. Min Act: -0.0000

Data Index: 797543 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.7492. Min Act: -0.0000

Data Index: 1274339 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 5.6504. Min Range: -5.6504

Max Act: 5.2328. Min Act: -0.0000

Data Index: 777595 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.6030. Min Act: -0.0000

Data Index: 163933 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.8851. Min Act: -0.0000

Data Index: 65102 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.8939. Min Act: -0.0000

Data Index: 1134774 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.6472. Min Act: -0.0000

Data Index: 919683 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.2210. Min Act: -0.0000

Data Index: 908655 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.2138. Min Act: -0.0000

Data Index: 1082509 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.3877. Min Act: -0.0000

Data Index: 871555 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.5154. Min Act: -0.0000

Data Index: 343379 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.4496. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.4080. Min Act: -0.0000

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.3675. Min Act: -0.0000

Data Index: 248428 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.0150. Min Act: -0.0000

Data Index: 553182 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.1652. Min Act: -0.0000

Data Index: 1294284 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 5.6504. Min Range: -5.6504

Max Act: 4.3139. Min Act: -0.0000

Data Index: 1315796 (C4 (Web Text))

Max Activating Token Index: 637