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

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

Neuron 3478 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0113. Min Act: -0.0002

Data Index: 95894 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0113. Min Act: -0.0002

Data Index: 727708 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1422570 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1389114 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0109. Min Act: -0.0002

Data Index: 105019 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1524117 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1537530 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1364864 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1487509 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1422581 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1472149 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1395622 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1470370 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0104. Min Act: -0.0002

Data Index: 560451 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0102. Min Act: -0.0002

Data Index: 983989 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1457108 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1317538 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1544649 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0103. Min Act: -0.0002

Data Index: 362864 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1393012 (Python Code)

Max Activating Token Index: 6