Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0001

Data Index: 446507 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0816. Min Act: -0.0001

Data Index: 789147 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1275557 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0740. Min Act: -0.0000

Data Index: 807530 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0705. Min Act: -0.0000

Data Index: 135712 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1219649 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0681. Min Act: -0.0000

Data Index: 663147 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0671. Min Act: -0.0001

Data Index: 311116 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0697. Min Act: -0.0001

Data Index: 898842 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1091321 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1327921 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0656. Min Act: -0.0001

Data Index: 427563 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0629. Min Act: -0.0000

Data Index: 559486 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0625. Min Act: -0.0000

Data Index: 200872 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0647. Min Act: -0.0000

Data Index: 482432 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1101090 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0679. Min Act: -0.0000

Data Index: 724471 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0613. Min Act: -0.0000

Data Index: 327857 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0608. Min Act: -0.0000

Data Index: 624756 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0634. Min Act: -0.0001

Data Index: 2784 (C4 (Web Text))

Max Activating Token Index: 198