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

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

Neuron 1341 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: 1.2113. Min Range: -1.2113

Max Act: 1.2113. Min Act: -0.0000

Data Index: 15149 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 1.2113. Min Range: -1.2113

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1592590 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 1.2113. Min Range: -1.2113

Max Act: 1.1667. Min Act: -0.0000

Data Index: 866269 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1376989 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1513143 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1075173 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.2113. Min Range: -1.2113

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1561388 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1374408 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.9203. Min Act: -0.0000

Data Index: 781552 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1455079 (Python Code)

Max Activating Token Index: 598

Text #10

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1399787 (Python Code)

Max Activating Token Index: 724

Text #11

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1366585 (Python Code)

Max Activating Token Index: 348

Text #12

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1568401 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1467800 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1488856 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1505076 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1463031 (Python Code)

Max Activating Token Index: 958

Text #17

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1551002 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1628777 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 1.2113. Min Range: -1.2113

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1649435 (Python Code)

Max Activating Token Index: 966