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

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

Neuron 3966 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.3702. Min Act: -0.0000

Data Index: 269489 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.2416. Min Act: -0.0000

Data Index: 1093169 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.1602. Min Act: -0.0000

Data Index: 367222 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.3241. Min Act: -0.0000

Data Index: 913300 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.2932. Min Act: -0.0000

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.3547. Min Act: -0.0000

Data Index: 1358609 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.2300. Min Act: -0.0000

Data Index: 550322 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.1609. Min Act: -0.0000

Data Index: 1261266 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.2714. Min Act: -0.0000

Data Index: 527780 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.1242. Min Act: -0.0000

Data Index: 258081 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.3702. Min Range: -2.3702

Max Act: 1.9786. Min Act: -0.0000

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0730. Min Act: -0.0000

Data Index: 66490 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0583. Min Act: -0.0000

Data Index: 1172484 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1215467 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0374. Min Act: -0.0000

Data Index: 753420 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 2.3702. Min Range: -2.3702

Max Act: 1.8029. Min Act: -0.0000

Data Index: 368146 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0158. Min Act: -0.0000

Data Index: 854599 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0043. Min Act: -0.0000

Data Index: 211148 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 2.3702. Min Range: -2.3702

Max Act: 1.9933. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 2.3702. Min Range: -2.3702

Max Act: 2.0900. Min Act: -0.0000

Data Index: 801481 (C4 (Web Text))

Max Activating Token Index: 160