Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3356 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1533286 (Python Code)

Max Activating Token Index: 742

Text #1

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1382966 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1417228 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1445794 (Python Code)

Max Activating Token Index: 993

Text #4

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1631263 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1449150 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1565136 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1436284 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1645217 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1606327 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1515951 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1387049 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1595827 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1391472 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1597632 (Python Code)

Max Activating Token Index: 318

Text #15

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1541521 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1657060 (Python Code)

Max Activating Token Index: 739

Text #17

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1529252 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1806. Min Act: -0.0000

Data Index: 875298 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1621195 (Python Code)

Max Activating Token Index: 553