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

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

Neuron 2051 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: 1.2502. Min Range: -1.2502

Max Act: 1.2502. Min Act: -0.0001

Data Index: 1640085 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.8245. Min Act: -0.0001

Data Index: 1591498 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.8215. Min Act: 0.0001

Data Index: 1475799 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7882. Min Act: -0.0001

Data Index: 28940 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7913. Min Act: -0.0001

Data Index: 191941 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7471. Min Act: -0.0000

Data Index: 276588 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7541. Min Act: 0.0001

Data Index: 1419999 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7302. Min Act: 0.0001

Data Index: 1378094 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7011. Min Act: 0.0000

Data Index: 1615085 (Python Code)

Max Activating Token Index: 248

Text #9

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7072. Min Act: -0.0001

Data Index: 224445 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7264. Min Act: -0.0001

Data Index: 1391480 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6777. Min Act: -0.0000

Data Index: 830825 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6702. Min Act: -0.0001

Data Index: 1074685 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6924. Min Act: -0.0001

Data Index: 76769 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6814. Min Act: 0.0001

Data Index: 1514378 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7074. Min Act: -0.0000

Data Index: 728584 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6333. Min Act: -0.0001

Data Index: 286066 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.7070. Min Act: -0.0000

Data Index: 538490 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1135703 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.6616. Min Act: 0.0001

Data Index: 1606054 (Python Code)

Max Activating Token Index: 209