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

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

Neuron 392 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1952. Min Range: -7.1952

Max Act: 7.1952. Min Act: -0.0001

Data Index: 1517384 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.5301. Min Act: -0.0001

Data Index: 1564013 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.0988. Min Act: -0.0001

Data Index: 1259906 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.3756. Min Act: -0.0001

Data Index: 1582734 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.1932. Min Act: -0.0001

Data Index: 1548461 (Python Code)

Max Activating Token Index: 178

Text #5

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.3772. Min Act: -0.0001

Data Index: 1461348 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.5408. Min Act: -0.0001

Data Index: 1655348 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.1712. Min Act: -0.0001

Data Index: 1368902 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 7.1952. Min Range: -7.1952

Max Act: 5.8984. Min Act: -0.0001

Data Index: 1593684 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.4468. Min Act: -0.0001

Data Index: 1625547 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.1605. Min Act: -0.0001

Data Index: 1370789 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.1621. Min Act: -0.0001

Data Index: 1345124 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.0821. Min Act: -0.0001

Data Index: 1616470 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.6212. Min Act: -0.0001

Data Index: 1364060 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.0138. Min Act: -0.0001

Data Index: 1622259 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.3201. Min Act: -0.0001

Data Index: 1567527 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.1696. Min Act: -0.0001

Data Index: 1490142 (Python Code)

Max Activating Token Index: 321

Text #17

Max Range: 7.1952. Min Range: -7.1952

Max Act: 6.2478. Min Act: -0.0001

Data Index: 1490700 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 7.1952. Min Range: -7.1952

Max Act: 5.6962. Min Act: -0.0001

Data Index: 960242 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 7.1952. Min Range: -7.1952

Max Act: 5.8028. Min Act: -0.0001

Data Index: 114810 (C4 (Web Text))

Max Activating Token Index: 608