Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4701 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8865. Min Act: -0.0000

Data Index: 743205 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8672. Min Act: -0.0000

Data Index: 497499 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.9027. Min Act: -0.0000

Data Index: 482608 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8767. Min Act: -0.0000

Data Index: 439084 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7930. Min Act: -0.0000

Data Index: 846966 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8435. Min Act: -0.0000

Data Index: 877849 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7641. Min Act: -0.0000

Data Index: 631808 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7620. Min Act: -0.0000

Data Index: 265445 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7257. Min Act: -0.0000

Data Index: 112588 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7838. Min Act: -0.0000

Data Index: 959565 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7636. Min Act: -0.0000

Data Index: 850936 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7863. Min Act: -0.0000

Data Index: 998928 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1576639 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1427041 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1590208 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7518. Min Act: -0.0000

Data Index: 783584 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6612. Min Act: -0.0000

Data Index: 945725 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1115510 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1407117 (Python Code)

Max Activating Token Index: 954

Text #19

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1601024 (Python Code)

Max Activating Token Index: 983