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

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

Neuron 2904 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.1348. Min Act: -0.0001

Data Index: 673597 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.1616. Min Act: -0.0002

Data Index: 58056 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0502. Min Act: -0.0002

Data Index: 839618 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0861. Min Act: -0.0001

Data Index: 487358 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0855. Min Act: -0.0001

Data Index: 674507 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0422. Min Act: -0.0001

Data Index: 1111366 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0696. Min Act: -0.0002

Data Index: 249149 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0254. Min Act: -0.0001

Data Index: 134113 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.1616. Min Range: -1.1616

Max Act: 1.0067. Min Act: -0.0002

Data Index: 1209015 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9782. Min Act: -0.0002

Data Index: 798770 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9335. Min Act: -0.0002

Data Index: 578103 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9286. Min Act: -0.0002

Data Index: 242690 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.8993. Min Act: -0.0001

Data Index: 935564 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9833. Min Act: -0.0001

Data Index: 1324883 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9512. Min Act: -0.0001

Data Index: 1240254 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9129. Min Act: -0.0002

Data Index: 270849 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9271. Min Act: -0.0002

Data Index: 847076 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9246. Min Act: -0.0002

Data Index: 520500 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9266. Min Act: -0.0002

Data Index: 1341407 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.1616. Min Range: -1.1616

Max Act: 0.9005. Min Act: -0.0002

Data Index: 1081021 (C4 (Web Text))

Max Activating Token Index: 74