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

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

Neuron 2893 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1351629 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.4037. Min Act: -0.0000

Data Index: 609323 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3397. Min Act: -0.0001

Data Index: 146787 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3458. Min Act: -0.0001

Data Index: 532862 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3202. Min Act: -0.0000

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1241859 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3067. Min Act: -0.0001

Data Index: 623081 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3258. Min Act: -0.0001

Data Index: 293169 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.3138. Min Act: -0.0001

Data Index: 900318 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2929. Min Act: -0.0000

Data Index: 559433 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2932. Min Act: -0.0001

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2918. Min Act: -0.0001

Data Index: 602111 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2701. Min Act: -0.0001

Data Index: 195739 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2700. Min Act: -0.0000

Data Index: 68551 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2702. Min Act: -0.0001

Data Index: 801481 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2648. Min Act: -0.0001

Data Index: 447854 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2656. Min Act: -0.0001

Data Index: 318756 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2523. Min Act: -0.0001

Data Index: 594363 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.4390. Min Range: -0.4390

Max Act: 0.2510. Min Act: -0.0000

Data Index: 593044 (C4 (Web Text))

Max Activating Token Index: 49