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

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

Neuron 831 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.8338. Min Act: -0.0001

Data Index: 812552 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6411. Min Act: -0.0001

Data Index: 210676 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6164. Min Act: -0.0000

Data Index: 586001 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.3995. Min Act: -0.0000

Data Index: 492781 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.3277. Min Act: -0.0001

Data Index: 453839 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.2583. Min Act: -0.0000

Data Index: 140712 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.2819. Min Act: -0.0001

Data Index: 1608494 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.2505. Min Act: -0.0000

Data Index: 648204 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.1787. Min Act: -0.0000

Data Index: 235735 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.4371. Min Act: -0.0001

Data Index: 26232 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0916. Min Act: -0.0001

Data Index: 507217 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.2369. Min Act: -0.0001

Data Index: 22129 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0757. Min Act: -0.0001

Data Index: 787154 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0663. Min Act: -0.0000

Data Index: 667496 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0695. Min Act: -0.0000

Data Index: 229626 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.2287. Min Act: -0.0001

Data Index: 268939 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1199334 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0784. Min Act: -0.0000

Data Index: 919555 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0728. Min Act: -0.0001

Data Index: 1342454 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.0959. Min Act: -0.0001

Data Index: 265840 (C4 (Web Text))

Max Activating Token Index: 502