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

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

Neuron 4028 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: 0.5251. Min Range: -0.5251

Max Act: 0.5235. Min Act: -0.0000

Data Index: 461114 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.5251. Min Act: -0.0000

Data Index: 963067 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.5228. Min Act: -0.0000

Data Index: 664224 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4872. Min Act: -0.0001

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4642. Min Act: -0.0001

Data Index: 632209 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4718. Min Act: -0.0001

Data Index: 954266 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1195684 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4770. Min Act: -0.0001

Data Index: 268517 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4424. Min Act: -0.0001

Data Index: 940735 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4382. Min Act: -0.0000

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4796. Min Act: -0.0001

Data Index: 515785 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4432. Min Act: -0.0001

Data Index: 624587 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4447. Min Act: -0.0000

Data Index: 714235 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4482. Min Act: -0.0001

Data Index: 832897 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4440. Min Act: -0.0000

Data Index: 674550 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4305. Min Act: 0.0000

Data Index: 1256594 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4154. Min Act: -0.0001

Data Index: 385957 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4317. Min Act: -0.0000

Data Index: 321553 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4206. Min Act: -0.0001

Data Index: 815450 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4204. Min Act: -0.0001

Data Index: 977290 (C4 (Web Text))

Max Activating Token Index: 873