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

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

Neuron 416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2664. Min Range: -4.2664

Max Act: 4.2664. Min Act: -0.0000

Data Index: 1097655 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 4.2664. Min Range: -4.2664

Max Act: 3.6329. Min Act: -0.0000

Data Index: 70387 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 4.2664. Min Range: -4.2664

Max Act: 3.4433. Min Act: -0.0000

Data Index: 306780 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 4.2664. Min Range: -4.2664

Max Act: 3.1321. Min Act: -0.0000

Data Index: 449153 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 4.2664. Min Range: -4.2664

Max Act: 3.3815. Min Act: -0.0000

Data Index: 68098 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.7163. Min Act: -0.0000

Data Index: 581763 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.7266. Min Act: -0.0000

Data Index: 220456 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.7575. Min Act: -0.0000

Data Index: 37618 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.6288. Min Act: -0.0000

Data Index: 1167875 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.6815. Min Act: -0.0000

Data Index: 814860 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.5000. Min Act: -0.0000

Data Index: 850749 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.3967. Min Act: -0.0000

Data Index: 530177 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.3579. Min Act: -0.0000

Data Index: 1052380 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.2436. Min Act: -0.0000

Data Index: 1205000 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.4719. Min Act: -0.0000

Data Index: 723538 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.3256. Min Act: -0.0000

Data Index: 1249021 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.4405. Min Act: -0.0000

Data Index: 1033186 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.1556. Min Act: -0.0000

Data Index: 374224 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.4904. Min Act: -0.0000

Data Index: 448687 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 4.2664. Min Range: -4.2664

Max Act: 2.3780. Min Act: -0.0000

Data Index: 764406 (C4 (Web Text))

Max Activating Token Index: 392