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

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

Neuron 3172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.7020. Min Act: -0.0000

Data Index: 683578 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.6404. Min Act: -0.0000

Data Index: 152358 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.6427. Min Act: -0.0000

Data Index: 713990 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1082969 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.5882. Min Act: -0.0000

Data Index: 613525 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1251071 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.6151. Min Act: -0.0000

Data Index: 821358 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.5084. Min Act: -0.0000

Data Index: 99306 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.5099. Min Act: -0.0000

Data Index: 874467 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4216. Min Act: -0.0000

Data Index: 871541 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4720. Min Act: -0.0000

Data Index: 406702 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1095523 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4724. Min Act: -0.0000

Data Index: 1333645 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4556. Min Act: -0.0000

Data Index: 105190 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1238648 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4326. Min Act: -0.0000

Data Index: 482478 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.3877. Min Act: -0.0000

Data Index: 340640 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4296. Min Act: -0.0000

Data Index: 732204 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1058856 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 1.7020. Min Range: -1.7020

Max Act: 1.3350. Min Act: -0.0000

Data Index: 773860 (C4 (Web Text))

Max Activating Token Index: 38