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

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

Neuron 902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.5377. Min Act: -0.0000

Data Index: 799968 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4716. Min Act: -0.0000

Data Index: 972990 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4944. Min Act: -0.0000

Data Index: 19712 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4763. Min Act: -0.0000

Data Index: 937439 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4884. Min Act: -0.0000

Data Index: 911476 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.5049. Min Act: -0.0000

Data Index: 24293 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4948. Min Act: -0.0000

Data Index: 872798 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4541. Min Act: -0.0000

Data Index: 890968 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4662. Min Act: -0.0000

Data Index: 571408 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4778. Min Act: -0.0000

Data Index: 151775 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4641. Min Act: -0.0000

Data Index: 322229 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4574. Min Act: -0.0001

Data Index: 741361 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4671. Min Act: -0.0000

Data Index: 276072 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1348163 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4515. Min Act: -0.0001

Data Index: 79916 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4473. Min Act: -0.0000

Data Index: 804020 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4145. Min Act: -0.0001

Data Index: 109899 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1043184 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1311013 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.5377. Min Range: -0.5377

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1141363 (C4 (Web Text))

Max Activating Token Index: 534