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

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

Neuron 888 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: 2.8760. Min Range: -2.8760

Max Act: 2.8382. Min Act: -0.0000

Data Index: 188244 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.8760. Min Act: -0.0000

Data Index: 385618 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.6903. Min Act: -0.0000

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.7280. Min Act: -0.0000

Data Index: 1008720 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.8430. Min Act: -0.0000

Data Index: 150208 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.7973. Min Act: -0.0000

Data Index: 419352 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.7026. Min Act: -0.0000

Data Index: 261883 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.5835. Min Act: -0.0000

Data Index: 594874 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.7073. Min Act: -0.0001

Data Index: 679113 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.5007. Min Act: -0.0000

Data Index: 116009 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.3300. Min Act: -0.0000

Data Index: 1283587 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.4084. Min Act: -0.0000

Data Index: 579650 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.3874. Min Act: -0.0000

Data Index: 475451 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.5023. Min Act: -0.0000

Data Index: 515675 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.4661. Min Act: -0.0000

Data Index: 280589 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.3494. Min Act: -0.0000

Data Index: 527215 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1315714 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.4704. Min Act: -0.0000

Data Index: 399347 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.4389. Min Act: -0.0000

Data Index: 699667 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 2.8760. Min Range: -2.8760

Max Act: 2.5731. Min Act: -0.0000

Data Index: 507047 (C4 (Web Text))

Max Activating Token Index: 478