Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0292. Min Act: -0.0002

Data Index: 294042 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0002

Data Index: 840246 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0279. Min Act: -0.0001

Data Index: 709128 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0277. Min Act: -0.0002

Data Index: 767912 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1567875 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0282. Min Act: -0.0001

Data Index: 944753 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1430955 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0249. Min Act: -0.0002

Data Index: 664415 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0276. Min Act: -0.0002

Data Index: 268235 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0264. Min Act: -0.0001

Data Index: 703327 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0272. Min Act: -0.0001

Data Index: 447674 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0272. Min Act: -0.0002

Data Index: 221243 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0266. Min Act: -0.0001

Data Index: 37071 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1317143 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1204040 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0272. Min Act: -0.0002

Data Index: 977056 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0264. Min Act: -0.0002

Data Index: 148305 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0288. Min Act: -0.0001

Data Index: 358124 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0276. Min Act: -0.0001

Data Index: 954129 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0268. Min Act: -0.0001

Data Index: 804665 (C4 (Web Text))

Max Activating Token Index: 935