Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 785 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1597. Min Act: -0.0001

Data Index: 3043 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1058937 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1020565 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1332. Min Act: -0.0001

Data Index: 879957 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1326. Min Act: -0.0001

Data Index: 752721 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1170. Min Act: -0.0001

Data Index: 237312 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1260. Min Act: -0.0001

Data Index: 208289 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1251. Min Act: -0.0001

Data Index: 169622 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1342. Min Act: -0.0001

Data Index: 487310 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1106970 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1125. Min Act: -0.0001

Data Index: 561404 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0991. Min Act: -0.0001

Data Index: 597807 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1275. Min Act: -0.0001

Data Index: 710262 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1164. Min Act: -0.0001

Data Index: 576963 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1025. Min Act: -0.0001

Data Index: 244777 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1086. Min Act: -0.0001

Data Index: 517423 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1164. Min Act: -0.0001

Data Index: 752440 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1339. Min Act: -0.0001

Data Index: 233178 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1151. Min Act: -0.0001

Data Index: 375565 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.0871. Min Act: -0.0001

Data Index: 745040 (C4 (Web Text))

Max Activating Token Index: 549