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

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

Neuron 1262 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: 3.2057. Min Range: -3.2057

Max Act: 3.1584. Min Act: 0.0000

Data Index: 1585719 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.2057. Min Act: -0.0000

Data Index: 1384110 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.8153. Min Act: -0.0000

Data Index: 1423256 (Python Code)

Max Activating Token Index: 922

Text #3

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.4547. Min Act: 0.0000

Data Index: 1564070 (Python Code)

Max Activating Token Index: 366

Text #4

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.5340. Min Act: -0.0000

Data Index: 1474123 (Python Code)

Max Activating Token Index: 551

Text #5

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.7807. Min Act: -0.0000

Data Index: 1371706 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.6064. Min Act: -0.0000

Data Index: 1573855 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 3.2057. Min Range: -3.2057

Max Act: 1.9213. Min Act: -0.0000

Data Index: 1550183 (Python Code)

Max Activating Token Index: 764

Text #8

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1554056 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1471216 (Python Code)

Max Activating Token Index: 940

Text #10

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.1003. Min Act: 0.0000

Data Index: 1517528 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.1019. Min Act: -0.0000

Data Index: 1478473 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.1735. Min Act: -0.0000

Data Index: 859626 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.1950. Min Act: -0.0000

Data Index: 1652293 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.1057. Min Act: -0.0000

Data Index: 1205000 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 3.2057. Min Range: -3.2057

Max Act: 1.9151. Min Act: -0.0000

Data Index: 1532690 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.0875. Min Act: 0.0000

Data Index: 1478422 (Python Code)

Max Activating Token Index: 368

Text #17

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.0930. Min Act: -0.0000

Data Index: 1579179 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.0191. Min Act: 0.0000

Data Index: 1460207 (Python Code)

Max Activating Token Index: 331

Text #19

Max Range: 3.2057. Min Range: -3.2057

Max Act: 1.9678. Min Act: -0.0000

Data Index: 1085764 (C4 (Web Text))

Max Activating Token Index: 445