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

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

Neuron 1980 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: 1.2461. Min Range: -1.2461

Max Act: 1.2461. Min Act: -0.0001

Data Index: 870663 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.2289. Min Act: -0.0001

Data Index: 1002908 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.1933. Min Act: -0.0001

Data Index: 265515 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.1701. Min Act: -0.0001

Data Index: 254350 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.2461. Min Range: -1.2461

Max Act: 0.9558. Min Act: -0.0001

Data Index: 726249 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.1119. Min Act: -0.0001

Data Index: 253615 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0904. Min Act: -0.0001

Data Index: 37782 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.1008. Min Act: -0.0001

Data Index: 578479 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0948. Min Act: -0.0001

Data Index: 565076 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0719. Min Act: -0.0001

Data Index: 467195 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0366. Min Act: -0.0001

Data Index: 68135 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0232. Min Act: -0.0001

Data Index: 116534 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0619. Min Act: -0.0001

Data Index: 146276 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0027. Min Act: -0.0001

Data Index: 1033106 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.2461. Min Range: -1.2461

Max Act: 0.9902. Min Act: -0.0001

Data Index: 173167 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.2461. Min Range: -1.2461

Max Act: 0.9811. Min Act: -0.0001

Data Index: 296292 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.2461. Min Range: -1.2461

Max Act: 0.9908. Min Act: -0.0001

Data Index: 712428 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 1.2461. Min Range: -1.2461

Max Act: 0.9868. Min Act: -0.0001

Data Index: 746486 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.2461. Min Range: -1.2461

Max Act: 1.0074. Min Act: -0.0001

Data Index: 546824 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.2461. Min Range: -1.2461

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1359115 (C4 (Web Text))

Max Activating Token Index: 682