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

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

Neuron 2384 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.9290. Min Act: -0.0000

Data Index: 642019 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.7382. Min Act: -0.0000

Data Index: 1350725 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.5349. Min Act: -0.0000

Data Index: 791505 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.4774. Min Act: -0.0000

Data Index: 1010844 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3881. Min Act: -0.0000

Data Index: 1328371 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3656. Min Act: -0.0000

Data Index: 152614 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3273. Min Act: -0.0000

Data Index: 1018702 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3168. Min Act: -0.0000

Data Index: 512496 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.2403. Min Act: -0.0000

Data Index: 653610 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.2328. Min Act: -0.0000

Data Index: 392169 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.1170. Min Act: -0.0000

Data Index: 10839 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.2360. Min Act: -0.0000

Data Index: 1109352 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.2369. Min Act: -0.0000

Data Index: 1312328 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.3291. Min Act: -0.0000

Data Index: 960153 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.2881. Min Act: -0.0000

Data Index: 687579 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.1653. Min Act: -0.0000

Data Index: 907203 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.1600. Min Act: -0.0000

Data Index: 44935 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.1570. Min Act: -0.0000

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.1402. Min Act: -0.0000

Data Index: 1175468 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 2.9290. Min Range: -2.9290

Max Act: 2.1404. Min Act: -0.0000

Data Index: 236591 (C4 (Web Text))

Max Activating Token Index: 512