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

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

Neuron 392 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: 0.9926. Min Range: -0.9926

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1544803 (Python Code)

Max Activating Token Index: 1022

Text #1

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1601229 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1598532 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8005. Min Act: -0.0000

Data Index: 59718 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1532125 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1159616 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1316702 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1525116 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8086. Min Act: -0.0000

Data Index: 870920 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1425430 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1394815 (Python Code)

Max Activating Token Index: 897

Text #11

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1647546 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1441056 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1615584 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1574921 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7576. Min Act: 0.0000

Data Index: 1572254 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1638712 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7501. Min Act: -0.0000

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1448150 (Python Code)

Max Activating Token Index: 212