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

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

Neuron 2005 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1588526 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1442839 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1561218 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1475364 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1413820 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1550197 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1644561 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1597740 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1484801 (Python Code)

Max Activating Token Index: 706

Text #9

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1376943 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1011853 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1381008 (Python Code)

Max Activating Token Index: 663

Text #12

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1367086 (Python Code)

Max Activating Token Index: 626

Text #13

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1449413 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1515354 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1423027 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1441712 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1407518 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1505403 (Python Code)

Max Activating Token Index: 463

Text #19

Max Range: 1.5130. Min Range: -1.5130

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1572336 (Python Code)

Max Activating Token Index: 826