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

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

Neuron 2256 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: 1.0145. Min Range: -1.0145

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1367710 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1369239 (Python Code)

Max Activating Token Index: 406

Text #2

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1504638 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1386492 (Python Code)

Max Activating Token Index: 507

Text #4

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1396811 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1488351 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1526024 (Python Code)

Max Activating Token Index: 247

Text #7

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1569695 (Python Code)

Max Activating Token Index: 752

Text #8

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1648986 (Python Code)

Max Activating Token Index: 985

Text #9

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1531409 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1528757 (Python Code)

Max Activating Token Index: 712

Text #11

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1620588 (Python Code)

Max Activating Token Index: 934

Text #12

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1652429 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1528097 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1426650 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1394057 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1419116 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1377448 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1369214 (Python Code)

Max Activating Token Index: 446

Text #19

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1631520 (Python Code)

Max Activating Token Index: 679