Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2166 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0930. Min Range: -1.0930

Max Act: 1.0796. Min Act: -0.0001

Data Index: 335905 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.0930. Min Range: -1.0930

Max Act: 1.0930. Min Act: -0.0001

Data Index: 1032215 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9584. Min Act: -0.0001

Data Index: 319684 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.0930. Min Range: -1.0930

Max Act: 1.0095. Min Act: -0.0001

Data Index: 444568 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1050380 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9497. Min Act: -0.0001

Data Index: 873743 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1280003 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9437. Min Act: -0.0001

Data Index: 1185874 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9062. Min Act: -0.0001

Data Index: 550841 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9246. Min Act: -0.0001

Data Index: 127057 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8742. Min Act: -0.0001

Data Index: 501347 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8674. Min Act: -0.0001

Data Index: 817434 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8396. Min Act: -0.0001

Data Index: 956134 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8315. Min Act: -0.0001

Data Index: 628986 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.9480. Min Act: -0.0001

Data Index: 850363 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8190. Min Act: -0.0001

Data Index: 1152381 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8361. Min Act: -0.0001

Data Index: 147762 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8112. Min Act: -0.0001

Data Index: 766223 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.7770. Min Act: -0.0001

Data Index: 133823 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.0930. Min Range: -1.0930

Max Act: 0.8908. Min Act: -0.0001

Data Index: 436833 (C4 (Web Text))

Max Activating Token Index: 874