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

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

Neuron 1144 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.2775. Min Act: -0.0001

Data Index: 780855 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1200452 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1917. Min Act: -0.0001

Data Index: 692520 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1969. Min Act: -0.0001

Data Index: 741396 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1135235 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1734. Min Act: -0.0001

Data Index: 297346 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1883. Min Act: -0.0001

Data Index: 988324 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1833. Min Act: -0.0001

Data Index: 227906 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1672. Min Act: -0.0001

Data Index: 830800 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1583. Min Act: -0.0001

Data Index: 500429 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1026182 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1255112 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1589. Min Act: -0.0001

Data Index: 339145 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1537. Min Act: -0.0001

Data Index: 940354 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1341. Min Act: -0.0001

Data Index: 867489 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1468. Min Act: -0.0001

Data Index: 164262 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1179812 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1504. Min Act: -0.0001

Data Index: 203580 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1608. Min Act: -0.0001

Data Index: 470894 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.2775. Min Range: -0.2775

Max Act: 0.1479. Min Act: -0.0001

Data Index: 844559 (C4 (Web Text))

Max Activating Token Index: 548