Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4777 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1614866 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.3346. Min Act: -0.0000

Data Index: 1379282 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1496498 (Python Code)

Max Activating Token Index: 534

Text #3

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1406382 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1533690 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2904. Min Act: -0.0000

Data Index: 1367473 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1440344 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1543113 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1568554 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0576. Min Act: -0.0000

Data Index: 1449723 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1360930 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1418468 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1501149 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0168. Min Act: -0.0000

Data Index: 1360837 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1503419 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1544557 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1382137 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1451266 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1646878 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1642351 (Python Code)

Max Activating Token Index: 748