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

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

Neuron 4803 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: 2.7160. Min Range: -2.7160

Max Act: 2.7160. Min Act: -0.0000

Data Index: 3217 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.6626. Min Act: -0.0000

Data Index: 262052 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.6289. Min Act: -0.0000

Data Index: 39930 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.4911. Min Act: -0.0000

Data Index: 1293235 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3705. Min Act: -0.0000

Data Index: 205687 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2404. Min Act: -0.0000

Data Index: 935461 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3486. Min Act: -0.0000

Data Index: 607166 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.1970. Min Act: -0.0000

Data Index: 855366 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.4022. Min Act: -0.0000

Data Index: 577606 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3145. Min Act: -0.0000

Data Index: 427661 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2941. Min Act: -0.0000

Data Index: 1042726 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.4060. Min Act: -0.0000

Data Index: 1298199 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.1392. Min Act: -0.0000

Data Index: 458498 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2574. Min Act: -0.0000

Data Index: 268727 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2619. Min Act: -0.0000

Data Index: 513764 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2260. Min Act: -0.0000

Data Index: 661219 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.2187. Min Act: -0.0000

Data Index: 465173 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.1895. Min Act: -0.0000

Data Index: 667560 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3333. Min Act: -0.0000

Data Index: 260591 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 2.7160. Min Range: -2.7160

Max Act: 2.3287. Min Act: -0.0000

Data Index: 507238 (C4 (Web Text))

Max Activating Token Index: 27