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

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

Neuron 1507 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9263. Min Range: -4.9263

Max Act: 4.9263. Min Act: -0.0000

Data Index: 1393765 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 4.9263. Min Range: -4.9263

Max Act: 3.5934. Min Act: -0.0000

Data Index: 1455334 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 4.9263. Min Range: -4.9263

Max Act: 3.2555. Min Act: -0.0000

Data Index: 1542463 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 4.9263. Min Range: -4.9263

Max Act: 3.4361. Min Act: -0.0000

Data Index: 1609104 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 4.9263. Min Range: -4.9263

Max Act: 3.0579. Min Act: -0.0000

Data Index: 1387186 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 4.9263. Min Range: -4.9263

Max Act: 3.0333. Min Act: -0.0000

Data Index: 1548757 (Python Code)

Max Activating Token Index: 715

Text #6

Max Range: 4.9263. Min Range: -4.9263

Max Act: 3.1297. Min Act: -0.0000

Data Index: 1519059 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.6900. Min Act: -0.0000

Data Index: 1607605 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.6495. Min Act: -0.0000

Data Index: 1424272 (Python Code)

Max Activating Token Index: 836

Text #9

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.4668. Min Act: -0.0000

Data Index: 1553532 (Python Code)

Max Activating Token Index: 632

Text #10

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.3572. Min Act: -0.0000

Data Index: 1488721 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.3729. Min Act: -0.0000

Data Index: 1487555 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.1776. Min Act: -0.0000

Data Index: 1638280 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1610495 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.0945. Min Act: -0.0000

Data Index: 1515463 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.0765. Min Act: -0.0000

Data Index: 1621056 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.0528. Min Act: -0.0000

Data Index: 1445385 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1491165 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1449479 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 4.9263. Min Range: -4.9263

Max Act: 2.0468. Min Act: -0.0000

Data Index: 1383458 (Python Code)

Max Activating Token Index: 546