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

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

Neuron 2269 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1079297 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2683. Min Act: -0.0000

Data Index: 433912 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2462. Min Act: -0.0000

Data Index: 123426 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2689. Min Act: -0.0000

Data Index: 964445 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2421. Min Act: -0.0000

Data Index: 57669 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2389. Min Act: -0.0000

Data Index: 492680 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1121737 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2285. Min Act: -0.0000

Data Index: 907490 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2613. Min Act: -0.0000

Data Index: 49091 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1025612 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1534994 (Python Code)

Max Activating Token Index: 319

Text #11

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1585678 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1011176 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1370470 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1531965 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1964. Min Act: -0.0000

Data Index: 725271 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1379637 (Python Code)

Max Activating Token Index: 583

Text #17

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1920. Min Act: -0.0000

Data Index: 27678 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1985. Min Act: -0.0000

Data Index: 589975 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1857. Min Act: -0.0000

Data Index: 324049 (C4 (Web Text))

Max Activating Token Index: 441