Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1831 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.9209. Min Act: -0.0001

Data Index: 413327 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.9521. Min Act: -0.0000

Data Index: 237925 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1330231 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8774. Min Act: -0.0000

Data Index: 437474 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8646. Min Act: -0.0000

Data Index: 861749 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1267147 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8307. Min Act: -0.0000

Data Index: 428231 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1341846 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8627. Min Act: -0.0001

Data Index: 780507 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1065 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1248063 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7783. Min Act: -0.0001

Data Index: 583123 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1266160 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7210. Min Act: -0.0001

Data Index: 801670 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7691. Min Act: -0.0000

Data Index: 162185 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7625. Min Act: -0.0001

Data Index: 436115 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.6956. Min Act: -0.0000

Data Index: 655215 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1268249 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.8729. Min Act: -0.0000

Data Index: 946067 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.9521. Min Range: -0.9521

Max Act: 0.7662. Min Act: -0.0000

Data Index: 597153 (C4 (Web Text))

Max Activating Token Index: 284