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

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

Neuron 4612 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: 1.2384. Min Range: -1.2384

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1167814 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.2298. Min Act: -0.0000

Data Index: 950576 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1379. Min Act: -0.0000

Data Index: 509721 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1078309 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1511. Min Act: -0.0000

Data Index: 810879 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1456. Min Act: -0.0000

Data Index: 346438 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.1596. Min Act: -0.0000

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0833. Min Act: -0.0000

Data Index: 701494 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0705. Min Act: -0.0000

Data Index: 427225 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0509. Min Act: -0.0000

Data Index: 527791 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0452. Min Act: -0.0000

Data Index: 374144 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1320236 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.2384. Min Range: -1.2384

Max Act: 1.0218. Min Act: -0.0000

Data Index: 364647 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.9394. Min Act: -0.0000

Data Index: 633325 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1074496 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1216590 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.9584. Min Act: -0.0000

Data Index: 446413 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1186757 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.9646. Min Act: -0.0000

Data Index: 792522 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.2384. Min Range: -1.2384

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1425033 (Python Code)

Max Activating Token Index: 624