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

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

Neuron 2563 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: 0.5497. Min Range: -0.5497

Max Act: 0.5433. Min Act: -0.0000

Data Index: 338643 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1133998 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4514. Min Act: -0.0000

Data Index: 594968 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1030717 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4248. Min Act: -0.0000

Data Index: 592057 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4747. Min Act: -0.0000

Data Index: 742783 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4601. Min Act: -0.0000

Data Index: 816548 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1017977 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1064167 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4483. Min Act: -0.0000

Data Index: 923781 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1047660 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1247733 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1062132 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4475. Min Act: -0.0000

Data Index: 821820 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4398. Min Act: -0.0000

Data Index: 269588 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1163534 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4623. Min Act: -0.0000

Data Index: 488581 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3428. Min Act: -0.0000

Data Index: 621186 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4020. Min Act: -0.0000

Data Index: 80590 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1062629 (C4 (Web Text))

Max Activating Token Index: 680