Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3441 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5944. Min Act: -0.0001

Data Index: 475558 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5763. Min Act: -0.0001

Data Index: 337574 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5614. Min Act: -0.0001

Data Index: 54460 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5351. Min Act: -0.0001

Data Index: 403961 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5700. Min Act: -0.0000

Data Index: 329136 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5546. Min Act: -0.0000

Data Index: 772649 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5144. Min Act: -0.0001

Data Index: 1046458 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5411. Min Act: -0.0001

Data Index: 351745 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4937. Min Act: -0.0001

Data Index: 216255 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5084. Min Act: -0.0001

Data Index: 438080 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4764. Min Act: -0.0000

Data Index: 654421 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1357764 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4795. Min Act: -0.0000

Data Index: 112657 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1091688 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5096. Min Act: -0.0001

Data Index: 376531 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4779. Min Act: -0.0001

Data Index: 899184 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1174735 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4883. Min Act: -0.0000

Data Index: 57021 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4689. Min Act: -0.0001

Data Index: 263922 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4691. Min Act: -0.0001

Data Index: 989122 (C4 (Web Text))

Max Activating Token Index: 56