Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1115 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1013439 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0412. Min Act: -0.0006

Data Index: 1546911 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1136089 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1490706 (Python Code)

Max Activating Token Index: 551

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1417787 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0381. Min Act: -0.0006

Data Index: 545239 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0388. Min Act: -0.0006

Data Index: 566766 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1424385 (Python Code)

Max Activating Token Index: 199

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1029040 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0382. Min Act: -0.0006

Data Index: 62932 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0365. Min Act: -0.0006

Data Index: 979692 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0353. Min Act: -0.0006

Data Index: 1637210 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0360. Min Act: -0.0006

Data Index: 1350246 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0365. Min Act: -0.0006

Data Index: 982073 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0348. Min Act: -0.0006

Data Index: 720658 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0348. Min Act: -0.0006

Data Index: 342442 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0354. Min Act: -0.0006

Data Index: 381263 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0342. Min Act: -0.0005

Data Index: 1053893 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0349. Min Act: -0.0006

Data Index: 671078 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1283834 (C4 (Web Text))

Max Activating Token Index: 702