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

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

Neuron 3640 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.5109. Min Act: -0.0001

Data Index: 985866 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.5274. Min Act: -0.0001

Data Index: 7076 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4712. Min Act: -0.0001

Data Index: 799928 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4698. Min Act: -0.0001

Data Index: 641968 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4665. Min Act: -0.0001

Data Index: 657526 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1013170 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4588. Min Act: -0.0001

Data Index: 82487 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4484. Min Act: -0.0001

Data Index: 394395 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1006555 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4521. Min Act: -0.0001

Data Index: 217321 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4654. Min Act: -0.0001

Data Index: 913060 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4695. Min Act: -0.0001

Data Index: 601845 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4306. Min Act: -0.0001

Data Index: 783719 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4422. Min Act: -0.0001

Data Index: 615178 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4543. Min Act: -0.0001

Data Index: 201556 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4080. Min Act: -0.0001

Data Index: 417849 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4425. Min Act: -0.0001

Data Index: 940253 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4258. Min Act: -0.0001

Data Index: 1145167 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4388. Min Act: -0.0001

Data Index: 152404 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.3905. Min Act: -0.0001

Data Index: 253494 (C4 (Web Text))

Max Activating Token Index: 589