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

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

Neuron 964 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.7536. Min Act: -0.0000

Data Index: 1618769 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.3147. Min Act: -0.0000

Data Index: 1439898 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.3074. Min Act: -0.0000

Data Index: 1651667 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.0830. Min Act: -0.0000

Data Index: 1472042 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.0831. Min Act: -0.0000

Data Index: 1472752 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.3921. Min Act: -0.0000

Data Index: 1543108 (Python Code)

Max Activating Token Index: 216

Text #6

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.4187. Min Act: -0.0000

Data Index: 1510744 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.8489. Min Act: -0.0000

Data Index: 1378844 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 4.7536. Min Range: -4.7536

Max Act: 4.3874. Min Act: -0.0000

Data Index: 1650352 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.9527. Min Act: -0.0000

Data Index: 1557151 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.8677. Min Act: -0.0000

Data Index: 1445849 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.8476. Min Act: -0.0000

Data Index: 1492679 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.6895. Min Act: -0.0000

Data Index: 1369077 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.6866. Min Act: -0.0000

Data Index: 1474228 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1477481 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.2892. Min Act: -0.0000

Data Index: 1573794 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.6911. Min Act: -0.0000

Data Index: 1440868 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.5761. Min Act: -0.0000

Data Index: 1556000 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.5589. Min Act: -0.0000

Data Index: 1510179 (Python Code)

Max Activating Token Index: 160

Text #19

Max Range: 4.7536. Min Range: -4.7536

Max Act: 3.5227. Min Act: -0.0000

Data Index: 1632712 (Python Code)

Max Activating Token Index: 657