Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3229. Min Act: -0.0001

Data Index: 241038 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3629. Min Act: -0.0001

Data Index: 1128722 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1349041 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3300. Min Act: -0.0001

Data Index: 77287 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3291. Min Act: -0.0000

Data Index: 346761 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2955. Min Act: -0.0000

Data Index: 721739 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1633696 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1224179 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2802. Min Act: -0.0000

Data Index: 27071 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2655. Min Act: -0.0001

Data Index: 423639 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2604. Min Act: -0.0001

Data Index: 488635 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.3071. Min Act: -0.0001

Data Index: 643089 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2377. Min Act: -0.0001

Data Index: 1071341 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2510. Min Act: -0.0001

Data Index: 624464 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1221150 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2484. Min Act: -0.0001

Data Index: 859649 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2508. Min Act: -0.0001

Data Index: 716328 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2360. Min Act: -0.0001

Data Index: 40202 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1429857 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 0.3629. Min Range: -0.3629

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1017765 (C4 (Web Text))

Max Activating Token Index: 398