Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6678. Min Range: -5.6678

Max Act: 5.6678. Min Act: -0.0001

Data Index: 728306 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.4981. Min Act: -0.0001

Data Index: 403326 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.4563. Min Act: -0.0001

Data Index: 979595 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.5725. Min Act: -0.0001

Data Index: 1019417 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.5497. Min Act: -0.0001

Data Index: 382070 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.3054. Min Act: -0.0001

Data Index: 1146830 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.2273. Min Act: -0.0001

Data Index: 226634 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.5647. Min Act: -0.0000

Data Index: 558739 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.5482. Min Act: -0.0001

Data Index: 576040 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.3751. Min Act: -0.0001

Data Index: 1246734 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.0237. Min Act: -0.0001

Data Index: 991833 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.3758. Min Act: -0.0001

Data Index: 469214 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 5.6678. Min Range: -5.6678

Max Act: 3.7718. Min Act: -0.0001

Data Index: 1357698 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 5.6678. Min Range: -5.6678

Max Act: 3.5570. Min Act: -0.0000

Data Index: 106139 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.2036. Min Act: -0.0001

Data Index: 986671 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 5.6678. Min Range: -5.6678

Max Act: 3.9237. Min Act: -0.0001

Data Index: 503732 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.0109. Min Act: -0.0001

Data Index: 1290377 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 5.6678. Min Range: -5.6678

Max Act: 3.7026. Min Act: -0.0001

Data Index: 592976 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 5.6678. Min Range: -5.6678

Max Act: 3.9365. Min Act: -0.0001

Data Index: 714630 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 5.6678. Min Range: -5.6678

Max Act: 4.3240. Min Act: -0.0001

Data Index: 552759 (C4 (Web Text))

Max Activating Token Index: 983