Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1452485 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1441276 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1437484 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1651774 (Python Code)

Max Activating Token Index: 950

Text #4

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1382656 (Python Code)

Max Activating Token Index: 425

Text #5

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1553620 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1468174 (Python Code)

Max Activating Token Index: 861

Text #7

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1370901 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1627938 (Python Code)

Max Activating Token Index: 182

Text #9

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0828. Min Act: -0.0001

Data Index: 1508803 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1652364 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1517444 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1387290 (Python Code)

Max Activating Token Index: 559

Text #13

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1601152 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1501205 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9581. Min Act: -0.0001

Data Index: 1629101 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1618677 (Python Code)

Max Activating Token Index: 411

Text #17

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9498. Min Act: -0.0001

Data Index: 1544801 (Python Code)

Max Activating Token Index: 1010

Text #18

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1582085 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9903. Min Act: -0.0001

Data Index: 1469827 (Python Code)

Max Activating Token Index: 164