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

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

Neuron 901 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.9292. Min Act: -0.0001

Data Index: 1360613 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6619. Min Act: -0.0001

Data Index: 1412720 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6710. Min Act: -0.0001

Data Index: 1399214 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6883. Min Act: -0.0001

Data Index: 1440084 (Python Code)

Max Activating Token Index: 173

Text #4

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5924. Min Act: -0.0001

Data Index: 1567717 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6298. Min Act: -0.0001

Data Index: 1510437 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6320. Min Act: -0.0001

Data Index: 1364002 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5852. Min Act: -0.0001

Data Index: 1457972 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6082. Min Act: -0.0001

Data Index: 1651366 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5870. Min Act: -0.0001

Data Index: 1505978 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.4334. Min Act: -0.0001

Data Index: 1593204 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5944. Min Act: -0.0001

Data Index: 1416558 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5084. Min Act: -0.0001

Data Index: 1518642 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5467. Min Act: -0.0001

Data Index: 1418388 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5019. Min Act: -0.0001

Data Index: 1469884 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.6316. Min Act: -0.0001

Data Index: 1479100 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5243. Min Act: -0.0001

Data Index: 1488123 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.5803. Min Act: -0.0001

Data Index: 1464850 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.4859. Min Act: -0.0001

Data Index: 1501711 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 1.9292. Min Range: -1.9292

Max Act: 1.4904. Min Act: -0.0001

Data Index: 1546114 (Python Code)

Max Activating Token Index: 666