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

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

Neuron 1427 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1458764 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1410919 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1526480 (Python Code)

Max Activating Token Index: 766

Text #3

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1459089 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1487325 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1553977 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1535135 (Python Code)

Max Activating Token Index: 570

Text #7

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1427094 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1642184 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1376207 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1457300 (Python Code)

Max Activating Token Index: 181

Text #11

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2034. Min Act: 0.0000

Data Index: 1615750 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1638408 (Python Code)

Max Activating Token Index: 985

Text #13

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.1959. Min Act: 0.0000

Data Index: 1407871 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1436422 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2169. Min Act: 0.0001

Data Index: 1407822 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1453149 (Python Code)

Max Activating Token Index: 323

Text #17

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1636316 (Python Code)

Max Activating Token Index: 518

Text #18

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1443104 (Python Code)

Max Activating Token Index: 787

Text #19

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1629809 (Python Code)

Max Activating Token Index: 29