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

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

Neuron 1073 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.6073. Min Act: -0.0001

Data Index: 54287 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4927. Min Act: -0.0000

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5567. Min Act: -0.0001

Data Index: 287147 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5727. Min Act: -0.0001

Data Index: 556392 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5093. Min Act: -0.0000

Data Index: 972904 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5028. Min Act: -0.0000

Data Index: 69638 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4990. Min Act: -0.0001

Data Index: 50250 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.5285. Min Act: 0.0000

Data Index: 305685 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4568. Min Act: -0.0001

Data Index: 170564 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4727. Min Act: -0.0000

Data Index: 996332 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4465. Min Act: -0.0001

Data Index: 484994 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4433. Min Act: -0.0001

Data Index: 1103065 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4340. Min Act: -0.0001

Data Index: 652999 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4640. Min Act: -0.0001

Data Index: 1000826 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4271. Min Act: -0.0000

Data Index: 391689 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1336798 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4558. Min Act: -0.0001

Data Index: 84345 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4178. Min Act: -0.0001

Data Index: 1236409 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4170. Min Act: -0.0000

Data Index: 114492 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.6073. Min Range: -0.6073

Max Act: 0.4146. Min Act: -0.0001

Data Index: 587352 (C4 (Web Text))

Max Activating Token Index: 577