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

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

Neuron 741 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.6343. Min Act: -0.0001

Data Index: 465417 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5486. Min Act: -0.0000

Data Index: 859951 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.5051. Min Act: -0.0001

Data Index: 178540 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4688. Min Act: -0.0001

Data Index: 635533 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4795. Min Act: -0.0000

Data Index: 335171 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4672. Min Act: -0.0001

Data Index: 750626 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4543. Min Act: -0.0000

Data Index: 50265 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4194. Min Act: -0.0000

Data Index: 551641 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4407. Min Act: -0.0001

Data Index: 1216853 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4237. Min Act: -0.0000

Data Index: 881679 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4300. Min Act: -0.0000

Data Index: 339033 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4419. Min Act: -0.0001

Data Index: 595618 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1330340 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1143993 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3976. Min Act: -0.0000

Data Index: 34284 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3266. Min Act: -0.0001

Data Index: 1123080 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4079. Min Act: -0.0001

Data Index: 14396 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3988. Min Act: -0.0001

Data Index: 946414 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.4074. Min Act: -0.0000

Data Index: 362743 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.6343. Min Range: -0.6343

Max Act: 0.3846. Min Act: -0.0000

Data Index: 92176 (C4 (Web Text))

Max Activating Token Index: 49