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

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

Neuron 5058 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: 1.5695. Min Range: -1.5695

Max Act: 1.5683. Min Act: -0.0000

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.5005. Min Act: -0.0000

Data Index: 8812 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1027745 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1284652 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.4670. Min Act: -0.0000

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.4628. Min Act: -0.0000

Data Index: 9685 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.4578. Min Act: -0.0000

Data Index: 359583 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1052786 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.3506. Min Act: -0.0000

Data Index: 350648 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.3840. Min Act: -0.0000

Data Index: 211519 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.2837. Min Act: -0.0000

Data Index: 906481 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.3517. Min Act: -0.0000

Data Index: 313279 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.3420. Min Act: -0.0000

Data Index: 545649 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.3706. Min Act: -0.0000

Data Index: 598532 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.2659. Min Act: 0.0001

Data Index: 201504 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.1791. Min Act: -0.0000

Data Index: 285002 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.2115. Min Act: -0.0000

Data Index: 107263 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1101145 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.2307. Min Act: -0.0000

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.5695. Min Range: -1.5695

Max Act: 1.2697. Min Act: -0.0000

Data Index: 424740 (C4 (Web Text))

Max Activating Token Index: 580