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

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

Neuron 1422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.5008. Min Act: -0.0000

Data Index: 656620 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1153459 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.4068. Min Act: -0.0000

Data Index: 294001 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.4516. Min Act: -0.0000

Data Index: 133019 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2145. Min Act: -0.0000

Data Index: 1151799 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1312. Min Act: -0.0000

Data Index: 536542 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2210. Min Act: -0.0000

Data Index: 660286 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1152. Min Act: -0.0000

Data Index: 347939 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1076673 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2425. Min Act: -0.0000

Data Index: 154180 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0971. Min Act: -0.0000

Data Index: 633979 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0247. Min Act: -0.0000

Data Index: 914365 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0056. Min Act: -0.0000

Data Index: 663581 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0956. Min Act: -0.0000

Data Index: 334225 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0629. Min Act: -0.0000

Data Index: 932739 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1338405 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 1.5731. Min Range: -1.5731

Max Act: 0.9957. Min Act: -0.0000

Data Index: 285841 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1155039 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0735. Min Act: -0.0000

Data Index: 524916 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.5731. Min Range: -1.5731

Max Act: 0.9811. Min Act: -0.0000

Data Index: 396396 (C4 (Web Text))

Max Activating Token Index: 261