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

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

Neuron 2640 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3597. Min Range: -4.3597

Max Act: 4.3597. Min Act: -0.0000

Data Index: 289925 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.7813. Min Act: -0.0000

Data Index: 399652 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.7506. Min Act: -0.0000

Data Index: 122799 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.7747. Min Act: -0.0000

Data Index: 1167548 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.7149. Min Act: -0.0000

Data Index: 426958 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.4915. Min Act: -0.0000

Data Index: 1180881 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.4627. Min Act: -0.0000

Data Index: 490009 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.4600. Min Act: -0.0000

Data Index: 306410 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.5729. Min Act: -0.0000

Data Index: 184692 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.5418. Min Act: -0.0000

Data Index: 918087 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.2601. Min Act: -0.0000

Data Index: 1197740 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.3508. Min Act: -0.0000

Data Index: 1221917 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.1985. Min Act: -0.0000

Data Index: 1323544 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.4758. Min Act: -0.0000

Data Index: 996448 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.2800. Min Act: -0.0000

Data Index: 1194729 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.2674. Min Act: -0.0000

Data Index: 1244277 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.5702. Min Act: -0.0000

Data Index: 935767 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.4137. Min Act: -0.0000

Data Index: 806254 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.4130. Min Act: -0.0000

Data Index: 632781 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 4.3597. Min Range: -4.3597

Max Act: 3.2496. Min Act: -0.0000

Data Index: 500645 (C4 (Web Text))

Max Activating Token Index: 497