Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3506 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.5397. Min Act: -0.0001

Data Index: 235984 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.3756. Min Act: -0.0001

Data Index: 63903 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2714. Min Act: -0.0001

Data Index: 1647152 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2341. Min Act: -0.0001

Data Index: 354269 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0914. Min Act: -0.0001

Data Index: 1595198 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.3238. Min Act: -0.0001

Data Index: 355107 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1668. Min Act: -0.0001

Data Index: 1057419 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2276. Min Act: -0.0001

Data Index: 1383224 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1709. Min Act: -0.0001

Data Index: 1441498 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2029. Min Act: -0.0001

Data Index: 116588 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1437. Min Act: -0.0001

Data Index: 110615 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1338. Min Act: -0.0001

Data Index: 410877 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1305. Min Act: -0.0001

Data Index: 1333584 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1065. Min Act: -0.0001

Data Index: 1193304 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1263. Min Act: -0.0001

Data Index: 1457671 (Python Code)

Max Activating Token Index: 147

Text #15

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0539. Min Act: -0.0001

Data Index: 1561951 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1368617 (Python Code)

Max Activating Token Index: 248

Text #17

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0880. Min Act: -0.0001

Data Index: 1506758 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0786. Min Act: -0.0001

Data Index: 505525 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0582. Min Act: -0.0001

Data Index: 1214303 (C4 (Web Text))

Max Activating Token Index: 794