Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5511 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0447. Min Range: -4.0447

Max Act: 4.0447. Min Act: -0.0002

Data Index: 685943 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.5939. Min Act: -0.0002

Data Index: 560633 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.5803. Min Act: -0.0002

Data Index: 393381 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.5382. Min Act: -0.0002

Data Index: 1083019 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.4657. Min Act: -0.0002

Data Index: 338775 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.5024. Min Act: -0.0002

Data Index: 972880 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3799. Min Act: -0.0002

Data Index: 882991 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.4588. Min Act: -0.0002

Data Index: 305962 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3688. Min Act: -0.0002

Data Index: 229274 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3378. Min Act: -0.0002

Data Index: 13199 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3721. Min Act: -0.0002

Data Index: 928792 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3411. Min Act: -0.0002

Data Index: 560060 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3106. Min Act: -0.0002

Data Index: 337289 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3340. Min Act: -0.0002

Data Index: 807045 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3765. Min Act: -0.0002

Data Index: 950509 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.2783. Min Act: -0.0002

Data Index: 406572 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3681. Min Act: -0.0002

Data Index: 1132071 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3745. Min Act: -0.0002

Data Index: 115994 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.3574. Min Act: -0.0002

Data Index: 485595 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 4.0447. Min Range: -4.0447

Max Act: 3.2807. Min Act: -0.0002

Data Index: 351983 (C4 (Web Text))

Max Activating Token Index: 13