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

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

Neuron 985 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0114. Min Range: -3.0114

Max Act: 3.0114. Min Act: -0.0000

Data Index: 1428241 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8071. Min Act: -0.0000

Data Index: 1557855 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8274. Min Act: -0.0000

Data Index: 1642348 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5228. Min Act: -0.0000

Data Index: 1491769 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5902. Min Act: -0.0000

Data Index: 1541108 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.7145. Min Act: -0.0000

Data Index: 1482191 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5754. Min Act: -0.0000

Data Index: 1528344 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5599. Min Act: -0.0000

Data Index: 1500289 (Python Code)

Max Activating Token Index: 678

Text #8

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.6800. Min Act: -0.0000

Data Index: 1554485 (Python Code)

Max Activating Token Index: 873

Text #9

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.4175. Min Act: -0.0000

Data Index: 1439214 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5164. Min Act: -0.0000

Data Index: 1409863 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1377160 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.3523. Min Act: -0.0000

Data Index: 1410958 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.4658. Min Act: -0.0000

Data Index: 1564485 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.4545. Min Act: -0.0000

Data Index: 1653076 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.4661. Min Act: -0.0000

Data Index: 1594854 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1438058 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.5543. Min Act: -0.0000

Data Index: 1497336 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.3746. Min Act: -0.0000

Data Index: 1624397 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.2705. Min Act: -0.0000

Data Index: 1606060 (Python Code)

Max Activating Token Index: 1020