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

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

Neuron 2892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.4256. Min Act: -0.0001

Data Index: 1566324 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1440474 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1503424 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.4099. Min Act: -0.0001

Data Index: 1429191 (Python Code)

Max Activating Token Index: 491

Text #4

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.4087. Min Act: -0.0001

Data Index: 1648253 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3645. Min Act: -0.0001

Data Index: 1651465 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1478231 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1457733 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3897. Min Act: -0.0001

Data Index: 1433633 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3855. Min Act: -0.0001

Data Index: 1626958 (Python Code)

Max Activating Token Index: 336

Text #10

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3548. Min Act: -0.0001

Data Index: 1611314 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3555. Min Act: -0.0001

Data Index: 1388544 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1452986 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3419. Min Act: -0.0001

Data Index: 1600185 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3584. Min Act: -0.0001

Data Index: 1575960 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3598. Min Act: -0.0001

Data Index: 1469489 (Python Code)

Max Activating Token Index: 612

Text #16

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3637. Min Act: -0.0001

Data Index: 1653485 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1427374 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3523. Min Act: -0.0001

Data Index: 1638136 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1444600 (Python Code)

Max Activating Token Index: 150