Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0002

Data Index: 212639 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1439069 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0471. Min Act: -0.0002

Data Index: 104168 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0466. Min Act: -0.0002

Data Index: 912036 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1250623 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1079367 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0416. Min Act: -0.0002

Data Index: 835495 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0435. Min Act: -0.0002

Data Index: 229107 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0434. Min Act: -0.0002

Data Index: 445673 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0429. Min Act: -0.0002

Data Index: 670987 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0424. Min Act: -0.0002

Data Index: 118580 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1140620 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0422. Min Act: -0.0002

Data Index: 804406 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0414. Min Act: -0.0002

Data Index: 578233 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1107116 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0407. Min Act: -0.0002

Data Index: 529355 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1425922 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0398. Min Act: -0.0002

Data Index: 924010 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0388. Min Act: -0.0002

Data Index: 209314 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0380. Min Act: -0.0002

Data Index: 990133 (C4 (Web Text))

Max Activating Token Index: 670