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

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

Neuron 4235 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2571. Min Range: -4.2571

Max Act: 4.2571. Min Act: -0.0000

Data Index: 1092496 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.9747. Min Act: -0.0000

Data Index: 109658 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.7936. Min Act: -0.0000

Data Index: 691458 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.5533. Min Act: -0.0000

Data Index: 343843 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.8217. Min Act: -0.0000

Data Index: 1364618 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.6070. Min Act: 0.0000

Data Index: 548526 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.4417. Min Act: -0.0000

Data Index: 442109 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.4598. Min Act: -0.0000

Data Index: 1435139 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.2492. Min Act: 0.0000

Data Index: 908817 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.4951. Min Act: -0.0000

Data Index: 112461 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.0803. Min Act: -0.0000

Data Index: 1324065 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.1755. Min Act: -0.0000

Data Index: 430328 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.2895. Min Act: 0.0000

Data Index: 1280900 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.1239. Min Act: -0.0000

Data Index: 376296 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.1799. Min Act: -0.0000

Data Index: 584730 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.0282. Min Act: -0.0000

Data Index: 806343 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 4.2571. Min Range: -4.2571

Max Act: 2.8542. Min Act: 0.0000

Data Index: 931719 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 4.2571. Min Range: -4.2571

Max Act: 2.9723. Min Act: -0.0000

Data Index: 310586 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.0944. Min Act: -0.0000

Data Index: 832331 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.2571. Min Range: -4.2571

Max Act: 2.9868. Min Act: -0.0000

Data Index: 773424 (C4 (Web Text))

Max Activating Token Index: 423