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

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

Neuron 2431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.5906. Min Act: -0.0000

Data Index: 1414832 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.1001. Min Act: -0.0000

Data Index: 1525949 (Python Code)

Max Activating Token Index: 262

Text #2

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1429372 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.7651. Min Act: -0.0000

Data Index: 1362472 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.4954. Min Act: -0.0000

Data Index: 1574164 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1474318 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.5117. Min Act: -0.0000

Data Index: 1442601 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1392272 (Python Code)

Max Activating Token Index: 527

Text #8

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1399856 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.4103. Min Act: -0.0000

Data Index: 1450638 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.3897. Min Act: -0.0000

Data Index: 1486497 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1538968 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.3823. Min Act: -0.0000

Data Index: 1605585 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1381783 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1398761 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1421972 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1566012 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1587615 (Python Code)

Max Activating Token Index: 409

Text #18

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1395170 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 2.5906. Min Range: -2.5906

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1533992 (Python Code)

Max Activating Token Index: 785