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

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

Neuron 781 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3470. Min Act: -0.0003

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3473. Min Act: -0.0003

Data Index: 427479 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3167. Min Act: -0.0003

Data Index: 838585 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3180. Min Act: -0.0003

Data Index: 653884 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3140. Min Act: -0.0003

Data Index: 375938 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3010. Min Act: -0.0003

Data Index: 249294 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3085. Min Act: -0.0003

Data Index: 175053 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2964. Min Act: -0.0003

Data Index: 1287741 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2990. Min Act: -0.0003

Data Index: 729830 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3041. Min Act: -0.0003

Data Index: 935572 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3122. Min Act: -0.0003

Data Index: 796908 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3089. Min Act: -0.0003

Data Index: 782789 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2966. Min Act: -0.0003

Data Index: 466607 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3079. Min Act: -0.0003

Data Index: 1236871 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2942. Min Act: -0.0003

Data Index: 1138381 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3144. Min Act: -0.0003

Data Index: 276527 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.3237. Min Act: -0.0003

Data Index: 518716 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2991. Min Act: -0.0003

Data Index: 583296 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2778. Min Act: -0.0003

Data Index: 307916 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.3473. Min Range: -0.3473

Max Act: 0.2678. Min Act: -0.0003

Data Index: 472349 (C4 (Web Text))

Max Activating Token Index: 705