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

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

Neuron 5772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0410. Min Range: -4.0410

Max Act: 4.0410. Min Act: -0.0000

Data Index: 405335 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 4.0410. Min Range: -4.0410

Max Act: 3.3657. Min Act: -0.0000

Data Index: 364186 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.7373. Min Act: -0.0000

Data Index: 26149 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.8784. Min Act: -0.0000

Data Index: 323169 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 4.0410. Min Range: -4.0410

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1110334 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.9618. Min Act: -0.0000

Data Index: 1275241 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.7922. Min Act: -0.0000

Data Index: 181220 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.8941. Min Act: -0.0000

Data Index: 51162 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.9116. Min Act: -0.0000

Data Index: 420151 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1007083 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.6414. Min Act: -0.0000

Data Index: 200704 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.5822. Min Act: -0.0000

Data Index: 849018 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.8227. Min Act: -0.0000

Data Index: 886059 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.5358. Min Act: -0.0000

Data Index: 516740 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.5257. Min Act: -0.0000

Data Index: 353194 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.2381. Min Act: -0.0000

Data Index: 317083 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.3736. Min Act: -0.0000

Data Index: 95654 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.7450. Min Act: -0.0000

Data Index: 1327211 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.5569. Min Act: -0.0000

Data Index: 1007726 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 4.0410. Min Range: -4.0410

Max Act: 2.6331. Min Act: -0.0000

Data Index: 300696 (C4 (Web Text))

Max Activating Token Index: 914