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

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

Neuron 767 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: 3.4363. Min Range: -3.4363

Max Act: 3.3005. Min Act: -0.0000

Data Index: 1630915 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.1567. Min Act: -0.0000

Data Index: 1443294 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.4363. Min Act: -0.0000

Data Index: 1481797 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.3099. Min Act: -0.0000

Data Index: 1395624 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.1270. Min Act: -0.0000

Data Index: 1561255 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.1282. Min Act: -0.0000

Data Index: 1462627 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.0324. Min Act: -0.0000

Data Index: 1363986 (Python Code)

Max Activating Token Index: 229

Text #7

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.8621. Min Act: -0.0000

Data Index: 1476527 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.1155. Min Act: -0.0000

Data Index: 1569338 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.9560. Min Act: -0.0000

Data Index: 1652410 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.9592. Min Act: -0.0000

Data Index: 1494782 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.8035. Min Act: -0.0000

Data Index: 1592811 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.0571. Min Act: -0.0000

Data Index: 1636901 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 3.4363. Min Range: -3.4363

Max Act: 3.0496. Min Act: -0.0000

Data Index: 1440702 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1429647 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.8762. Min Act: -0.0000

Data Index: 1484957 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.7124. Min Act: -0.0000

Data Index: 1388455 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1428404 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.7901. Min Act: -0.0000

Data Index: 1593188 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 3.4363. Min Range: -3.4363

Max Act: 2.9366. Min Act: -0.0000

Data Index: 1387432 (Python Code)

Max Activating Token Index: 175