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

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

Neuron 2078 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: 0.2598. Min Range: -0.2598

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1388490 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1446006 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1509162 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1414134 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1560243 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1389534 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1506610 (Python Code)

Max Activating Token Index: 946

Text #7

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1549293 (Python Code)

Max Activating Token Index: 990

Text #8

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1547395 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1533991 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1380731 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1646554 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1427662 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1485205 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1434581 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1648288 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1549577 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1409687 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1456848 (Python Code)

Max Activating Token Index: 277

Text #19

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1530790 (Python Code)

Max Activating Token Index: 286