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

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

Neuron 4502 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0001

Data Index: 838237 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1215832 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1293279 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0384. Min Act: -0.0001

Data Index: 304396 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1048486 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1276576 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0373. Min Act: -0.0001

Data Index: 78644 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0355. Min Act: -0.0001

Data Index: 579864 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0341. Min Act: -0.0001

Data Index: 579398 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0339. Min Act: -0.0001

Data Index: 509993 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0354. Min Act: -0.0001

Data Index: 824224 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0333. Min Act: -0.0001

Data Index: 450797 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1198750 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0335. Min Act: -0.0001

Data Index: 512377 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0347. Min Act: -0.0001

Data Index: 558743 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0346. Min Act: -0.0001

Data Index: 376039 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0332. Min Act: -0.0001

Data Index: 825819 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1214633 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0319. Min Act: -0.0001

Data Index: 48362 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0303. Min Act: -0.0001

Data Index: 136215 (C4 (Web Text))

Max Activating Token Index: 841