Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 631 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1172817 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.4458. Min Act: -0.0000

Data Index: 509696 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3982. Min Act: -0.0000

Data Index: 309069 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3569. Min Act: -0.0000

Data Index: 310259 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3969. Min Act: -0.0000

Data Index: 461445 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1019635 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3410. Min Act: -0.0000

Data Index: 575249 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3552. Min Act: -0.0000

Data Index: 346861 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1128324 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3516. Min Act: -0.0000

Data Index: 803328 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3433. Min Act: -0.0000

Data Index: 858876 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1533078 (Python Code)

Max Activating Token Index: 415

Text #12

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1501294 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1512258 (Python Code)

Max Activating Token Index: 685

Text #14

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2561. Min Act: -0.0000

Data Index: 397964 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1615802 (Python Code)

Max Activating Token Index: 709

Text #16

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1591634 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1643095 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1491442 (Python Code)

Max Activating Token Index: 425

Text #19

Max Range: 0.4734. Min Range: -0.4734

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1530526 (Python Code)

Max Activating Token Index: 507