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

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

Neuron 624 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1153555 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.4533. Min Act: -0.0000

Data Index: 465004 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.3688. Min Act: -0.0000

Data Index: 395948 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1007406 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.4073. Min Act: -0.0000

Data Index: 339146 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.3633. Min Act: -0.0000

Data Index: 547070 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.2805. Min Act: -0.0000

Data Index: 65239 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.2642. Min Act: -0.0000

Data Index: 106560 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.3246. Min Act: -0.0000

Data Index: 577196 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1093587 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.2156. Min Act: -0.0000

Data Index: 592343 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1965. Min Act: -0.0000

Data Index: 767110 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1190. Min Act: -0.0000

Data Index: 683599 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1799. Min Act: -0.0000

Data Index: 488108 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1367. Min Act: -0.0000

Data Index: 729244 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1622. Min Act: -0.0000

Data Index: 195402 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1014083 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.2202. Min Act: -0.0000

Data Index: 315072 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1084745 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.4533. Min Range: -1.4533

Max Act: 1.0572. Min Act: -0.0000

Data Index: 909592 (C4 (Web Text))

Max Activating Token Index: 757