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

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

Neuron 4887 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: 0.8101. Min Range: -0.8101

Max Act: 0.8101. Min Act: -0.0000

Data Index: 6122 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5126. Min Act: -0.0000

Data Index: 526107 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5506. Min Act: -0.0000

Data Index: 392015 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.4870. Min Act: -0.0000

Data Index: 28795 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.4814. Min Act: -0.0000

Data Index: 695625 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3828. Min Act: -0.0000

Data Index: 61812 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3510. Min Act: -0.0000

Data Index: 753173 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3701. Min Act: -0.0000

Data Index: 56958 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1081696 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3738. Min Act: -0.0000

Data Index: 109834 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3617. Min Act: -0.0000

Data Index: 377637 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1330351 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3750. Min Act: -0.0000

Data Index: 912365 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3593. Min Act: -0.0000

Data Index: 199505 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1079905 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3716. Min Act: -0.0000

Data Index: 143109 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3579. Min Act: -0.0000

Data Index: 999166 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3230. Min Act: -0.0000

Data Index: 495465 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3332. Min Act: -0.0000

Data Index: 75995 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.3312. Min Act: -0.0000

Data Index: 291301 (C4 (Web Text))

Max Activating Token Index: 924