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

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

Neuron 2823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1352. Min Range: -2.1352

Max Act: 2.1352. Min Act: -0.0000

Data Index: 397281 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.1352. Min Range: -2.1352

Max Act: 2.0397. Min Act: -0.0000

Data Index: 514558 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 2.1352. Min Range: -2.1352

Max Act: 2.0959. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1386314 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1436095 (Python Code)

Max Activating Token Index: 912

Text #5

Max Range: 2.1352. Min Range: -2.1352

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1448100 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.7276. Min Act: -0.0000

Data Index: 845115 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.6526. Min Act: -0.0000

Data Index: 282286 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.7314. Min Act: -0.0000

Data Index: 1459725 (Python Code)

Max Activating Token Index: 547

Text #9

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.7225. Min Act: -0.0000

Data Index: 1569894 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5660. Min Act: -0.0000

Data Index: 616190 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1118328 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5782. Min Act: -0.0000

Data Index: 964689 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5330. Min Act: -0.0000

Data Index: 902764 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5476. Min Act: -0.0000

Data Index: 417874 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1508957 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1387070 (Python Code)

Max Activating Token Index: 215

Text #17

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1536614 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.5667. Min Act: -0.0000

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 2.1352. Min Range: -2.1352

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1513768 (Python Code)

Max Activating Token Index: 327