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

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

Neuron 554 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: 0.8566. Min Range: -0.8566

Max Act: 0.8566. Min Act: -0.0000

Data Index: 197397 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8555. Min Act: -0.0001

Data Index: 1603009 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7799. Min Act: -0.0000

Data Index: 516536 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1503728 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1114508 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1189103 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7745. Min Act: -0.0000

Data Index: 539115 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7932. Min Act: -0.0001

Data Index: 1411684 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7416. Min Act: -0.0001

Data Index: 1182009 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1200715 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7125. Min Act: -0.0000

Data Index: 506270 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7832. Min Act: -0.0001

Data Index: 1508199 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7436. Min Act: -0.0001

Data Index: 542134 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1407437 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1517498 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7295. Min Act: -0.0000

Data Index: 87788 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7364. Min Act: -0.0001

Data Index: 1469369 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1108518 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7222. Min Act: -0.0001

Data Index: 1415983 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6779. Min Act: -0.0001

Data Index: 246039 (C4 (Web Text))

Max Activating Token Index: 852