Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 822 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0003

Data Index: 805454 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1199870 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0509. Min Act: -0.0002

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1606479 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0519. Min Act: -0.0003

Data Index: 293248 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0501. Min Act: -0.0003

Data Index: 863085 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0518. Min Act: -0.0003

Data Index: 175314 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0534. Min Act: -0.0003

Data Index: 588055 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0502. Min Act: -0.0003

Data Index: 155357 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1054347 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0501. Min Act: -0.0002

Data Index: 51848 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0482. Min Act: -0.0003

Data Index: 649604 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1155537 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1308721 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1099864 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0486. Min Act: -0.0004

Data Index: 188144 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0511. Min Act: -0.0004

Data Index: 1017244 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0455. Min Act: -0.0003

Data Index: 777787 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1073687 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1061001 (C4 (Web Text))

Max Activating Token Index: 537