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

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

Neuron 3951 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6659. Min Act: -0.0001

Data Index: 910436 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1224263 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5568. Min Act: -0.0000

Data Index: 81123 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4817. Min Act: -0.0001

Data Index: 817730 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1178338 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4808. Min Act: -0.0000

Data Index: 690525 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5132. Min Act: -0.0000

Data Index: 590680 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1350703 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5209. Min Act: -0.0000

Data Index: 559488 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4687. Min Act: -0.0001

Data Index: 229785 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4832. Min Act: -0.0001

Data Index: 898495 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4577. Min Act: -0.0001

Data Index: 328504 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1051119 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.5121. Min Act: -0.0001

Data Index: 834766 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4479. Min Act: -0.0001

Data Index: 394221 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4379. Min Act: -0.0000

Data Index: 651563 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4333. Min Act: -0.0000

Data Index: 206849 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4279. Min Act: -0.0000

Data Index: 853988 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1050192 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.6659. Min Range: -0.6659

Max Act: 0.4322. Min Act: -0.0001

Data Index: 130187 (C4 (Web Text))

Max Activating Token Index: 290