Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6494. Min Act: -0.0000

Data Index: 351876 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5990. Min Act: -0.0000

Data Index: 447310 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6324. Min Act: -0.0000

Data Index: 944347 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5737. Min Act: -0.0000

Data Index: 387900 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5603. Min Act: -0.0000

Data Index: 374022 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5101. Min Act: -0.0000

Data Index: 802152 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5227. Min Act: -0.0000

Data Index: 139643 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4763. Min Act: -0.0000

Data Index: 874887 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5131. Min Act: -0.0000

Data Index: 339401 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5152. Min Act: -0.0000

Data Index: 523230 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5327. Min Act: -0.0000

Data Index: 902486 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5251. Min Act: -0.0000

Data Index: 282775 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1118700 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4976. Min Act: -0.0000

Data Index: 567090 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4666. Min Act: -0.0000

Data Index: 628449 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1135636 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4668. Min Act: -0.0000

Data Index: 118746 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4989. Min Act: -0.0000

Data Index: 579573 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4679. Min Act: -0.0000

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4647. Min Act: -0.0000

Data Index: 279510 (C4 (Web Text))

Max Activating Token Index: 386