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

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

Neuron 832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0118. Min Range: -1.0118

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1468926 (Python Code)

Max Activating Token Index: 303

Text #1

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1113536 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8976. Min Act: -0.0000

Data Index: 670357 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1479937 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8524. Min Act: -0.0000

Data Index: 388018 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1497524 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1364718 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1573981 (Python Code)

Max Activating Token Index: 538

Text #8

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1380113 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1176802 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8071. Min Act: -0.0000

Data Index: 356315 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.8297. Min Act: -0.0000

Data Index: 753860 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1593313 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1302800 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7061. Min Act: -0.0000

Data Index: 263231 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7900. Min Act: -0.0000

Data Index: 256497 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7889. Min Act: -0.0000

Data Index: 993140 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1451441 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7370. Min Act: -0.0000

Data Index: 632369 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.0118. Min Range: -1.0118

Max Act: 0.7653. Min Act: -0.0001

Data Index: 104792 (C4 (Web Text))

Max Activating Token Index: 27