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

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

Neuron 4831 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0002

Data Index: 569054 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0515. Min Act: -0.0002

Data Index: 484893 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0459. Min Act: -0.0002

Data Index: 353050 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0464. Min Act: -0.0002

Data Index: 326612 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0470. Min Act: -0.0002

Data Index: 111618 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0455. Min Act: -0.0002

Data Index: 890229 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1293783 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0442. Min Act: -0.0002

Data Index: 221201 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1332422 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0399. Min Act: -0.0002

Data Index: 635355 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0422. Min Act: -0.0002

Data Index: 598063 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0410. Min Act: -0.0002

Data Index: 873977 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1340441 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0371. Min Act: -0.0002

Data Index: 334573 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0388. Min Act: -0.0002

Data Index: 474697 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0362. Min Act: -0.0002

Data Index: 867673 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0346. Min Act: -0.0002

Data Index: 192669 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0372. Min Act: -0.0002

Data Index: 29988 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1306850 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0331. Min Act: -0.0002

Data Index: 13696 (C4 (Web Text))

Max Activating Token Index: 472