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

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

Neuron 2916 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1375573 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1409750 (Python Code)

Max Activating Token Index: 491

Text #2

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1414588 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1616485 (Python Code)

Max Activating Token Index: 514

Text #4

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1628263 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1527081 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1571482 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1467707 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1494845 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1549913 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1644245 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1403511 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1454259 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1601636 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1414498 (Python Code)

Max Activating Token Index: 282

Text #15

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1504973 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1468689 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1655085 (Python Code)

Max Activating Token Index: 734

Text #18

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1469208 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1383072 (Python Code)

Max Activating Token Index: 389