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

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

Neuron 1908 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.9377. Min Act: 0.0000

Data Index: 1631436 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.4792. Min Act: -0.0000

Data Index: 1390888 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.7885. Min Act: -0.0000

Data Index: 1446717 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.5642. Min Act: 0.0000

Data Index: 1564650 (Python Code)

Max Activating Token Index: 309

Text #4

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.7382. Min Act: -0.0000

Data Index: 1620045 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.4862. Min Act: -0.0000

Data Index: 1656620 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.5751. Min Act: 0.0000

Data Index: 1639136 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.0736. Min Act: -0.0000

Data Index: 1476136 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.5999. Min Act: -0.0000

Data Index: 1548938 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.1985. Min Act: -0.0000

Data Index: 1418801 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.5212. Min Act: 0.0000

Data Index: 1634749 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.9811. Min Act: 0.0000

Data Index: 1542095 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 5.9377. Min Range: -5.9377

Max Act: 5.1335. Min Act: -0.0000

Data Index: 1376626 (Python Code)

Max Activating Token Index: 744

Text #13

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.9554. Min Act: -0.0000

Data Index: 1364744 (Python Code)

Max Activating Token Index: 695

Text #14

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.8998. Min Act: -0.0000

Data Index: 1605214 (Python Code)

Max Activating Token Index: 594

Text #15

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.8239. Min Act: -0.0000

Data Index: 1571068 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.8151. Min Act: -0.0000

Data Index: 1544640 (Python Code)

Max Activating Token Index: 463

Text #17

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.4699. Min Act: -0.0000

Data Index: 1637426 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.4521. Min Act: 0.0000

Data Index: 1535714 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 5.9377. Min Range: -5.9377

Max Act: 4.4422. Min Act: -0.0000

Data Index: 1432016 (Python Code)

Max Activating Token Index: 376