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

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

Neuron 3717 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7790. Min Act: -0.0000

Data Index: 525610 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6280. Min Act: -0.0000

Data Index: 270954 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6152. Min Act: -0.0000

Data Index: 239637 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6240. Min Act: 0.0001

Data Index: 423068 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5881. Min Act: -0.0000

Data Index: 95577 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5738. Min Act: 0.0000

Data Index: 935480 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5367. Min Act: -0.0000

Data Index: 137987 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.4921. Min Act: -0.0000

Data Index: 206250 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5408. Min Act: -0.0000

Data Index: 133820 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5213. Min Act: -0.0000

Data Index: 150630 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5017. Min Act: -0.0000

Data Index: 911766 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5428. Min Act: -0.0000

Data Index: 949146 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5103. Min Act: -0.0000

Data Index: 595853 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1211682 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1242736 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.4921. Min Act: -0.0000

Data Index: 352525 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1076797 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.4751. Min Act: -0.0000

Data Index: 155391 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1007829 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1341447 (C4 (Web Text))

Max Activating Token Index: 30