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

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

Neuron 27 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1603. Min Act: -0.0001

Data Index: 194919 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0001

Data Index: 623968 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1599. Min Act: -0.0001

Data Index: 864873 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1564058 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1478269 (Python Code)

Max Activating Token Index: 856

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1538. Min Act: -0.0001

Data Index: 823647 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1387. Min Act: -0.0001

Data Index: 967389 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1183. Min Act: -0.0001

Data Index: 86661 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1465308 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1280. Min Act: -0.0001

Data Index: 760852 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1431466 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1653496 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1174043 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1368. Min Act: -0.0001

Data Index: 580530 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1399178 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1638265 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1463. Min Act: -0.0001

Data Index: 291284 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1259. Min Act: -0.0001

Data Index: 1389658 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1275. Min Act: -0.0001

Data Index: 889503 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1631462 (Python Code)

Max Activating Token Index: 891