Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1675 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3273. Min Act: -0.0002

Data Index: 1596599 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3052. Min Act: -0.0002

Data Index: 1445954 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2994. Min Act: -0.0003

Data Index: 767802 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2745. Min Act: -0.0002

Data Index: 1577795 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2722. Min Act: -0.0002

Data Index: 1629155 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2669. Min Act: -0.0002

Data Index: 1434260 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2651. Min Act: -0.0002

Data Index: 1509983 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2587. Min Act: -0.0002

Data Index: 1460444 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2255. Min Act: -0.0002

Data Index: 1486944 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2244. Min Act: -0.0003

Data Index: 314755 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2265. Min Act: -0.0003

Data Index: 563192 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2141. Min Act: -0.0003

Data Index: 1056103 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2123. Min Act: -0.0002

Data Index: 1572328 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2045. Min Act: -0.0003

Data Index: 316400 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2101. Min Act: -0.0002

Data Index: 1541972 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.1981. Min Act: -0.0003

Data Index: 440447 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.1957. Min Act: -0.0002

Data Index: 1606112 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.1935. Min Act: -0.0002

Data Index: 1414521 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.1926. Min Act: -0.0002

Data Index: 1399648 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.1991. Min Act: -0.0002

Data Index: 628045 (C4 (Web Text))

Max Activating Token Index: 9