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

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

Neuron 1585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2973. Min Act: -0.0000

Data Index: 215095 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2696. Min Act: -0.0000

Data Index: 826230 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1132101 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2575. Min Act: -0.0000

Data Index: 805958 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1088792 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1110330 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2621. Min Act: -0.0000

Data Index: 890967 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2684. Min Act: -0.0000

Data Index: 179416 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2280. Min Act: -0.0000

Data Index: 471830 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2154. Min Act: -0.0000

Data Index: 736170 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2189. Min Act: -0.0000

Data Index: 233034 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2300. Min Act: -0.0000

Data Index: 194166 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1090631 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2196. Min Act: -0.0000

Data Index: 792816 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2381. Min Act: -0.0000

Data Index: 515107 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2047. Min Act: -0.0000

Data Index: 139264 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2214. Min Act: -0.0000

Data Index: 56014 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2309. Min Act: -0.0000

Data Index: 434152 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2296. Min Act: -0.0000

Data Index: 664418 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2168. Min Act: -0.0000

Data Index: 834988 (C4 (Web Text))

Max Activating Token Index: 350