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

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

Neuron 5044 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1523231 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1420908 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1558908 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1372637 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1384396 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1437311 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1439108 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1488277 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1642485 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1559619 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1535133 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1381631 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1531368 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1599636 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1502261 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1516819 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1419042 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1429414 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1369872 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1604402 (Python Code)

Max Activating Token Index: 130