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

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

Neuron 272 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: 1.2137. Min Range: -1.2137

Max Act: 1.2137. Min Act: -0.0001

Data Index: 1407102 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1374277 (Python Code)

Max Activating Token Index: 294

Text #2

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1649191 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0270. Min Act: -0.0001

Data Index: 1431746 (Python Code)

Max Activating Token Index: 581

Text #4

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1525767 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9172. Min Act: -0.0001

Data Index: 1651475 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1389714 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1464459 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1410987 (Python Code)

Max Activating Token Index: 674

Text #9

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9359. Min Act: -0.0001

Data Index: 1430598 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8710. Min Act: -0.0001

Data Index: 1516618 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1369078 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1460229 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1656667 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1586786 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1409603 (Python Code)

Max Activating Token Index: 635

Text #16

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1486961 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1543920 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.7230. Min Act: -0.0001

Data Index: 1605958 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8143. Min Act: -0.0001

Data Index: 1392924 (Python Code)

Max Activating Token Index: 473