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

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

Neuron 1678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.6918. Min Act: -0.0000

Data Index: 830642 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.4106. Min Act: -0.0001

Data Index: 493462 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3646. Min Act: -0.0000

Data Index: 271949 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3478. Min Act: -0.0001

Data Index: 461372 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3250. Min Act: -0.0001

Data Index: 12612 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3484. Min Act: -0.0000

Data Index: 255352 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1282334 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3256. Min Act: -0.0000

Data Index: 283753 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3100. Min Act: -0.0000

Data Index: 543194 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1093594 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3139. Min Act: -0.0001

Data Index: 671201 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2898. Min Act: -0.0001

Data Index: 460137 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2508. Min Act: -0.0001

Data Index: 338722 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1014367 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.3081. Min Act: -0.0001

Data Index: 724573 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2703. Min Act: -0.0001

Data Index: 809867 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2887. Min Act: -0.0001

Data Index: 442765 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1475416 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2759. Min Act: -0.0000

Data Index: 946455 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.6918. Min Range: -0.6918

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1135390 (C4 (Web Text))

Max Activating Token Index: 27