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

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

Neuron 5327 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4878. Min Range: -2.4878

Max Act: 2.4878. Min Act: -0.0000

Data Index: 39926 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.4878. Min Range: -2.4878

Max Act: 2.1057. Min Act: -0.0000

Data Index: 283943 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.9124. Min Act: -0.0001

Data Index: 748499 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.8884. Min Act: -0.0001

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.8163. Min Act: -0.0001

Data Index: 2210 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5967. Min Act: -0.0001

Data Index: 36846 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5727. Min Act: -0.0000

Data Index: 19280 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5266. Min Act: -0.0001

Data Index: 686482 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5903. Min Act: -0.0000

Data Index: 396096 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5096. Min Act: -0.0000

Data Index: 1044934 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5321. Min Act: -0.0001

Data Index: 178247 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1313642 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1185855 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.3657. Min Act: -0.0001

Data Index: 1081423 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.2625. Min Act: -0.0000

Data Index: 867744 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.1806. Min Act: -0.0001

Data Index: 931906 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.2557. Min Act: -0.0001

Data Index: 1341213 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.2094. Min Act: -0.0001

Data Index: 290356 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.1543. Min Act: -0.0000

Data Index: 11047 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 2.4878. Min Range: -2.4878

Max Act: 1.2975. Min Act: -0.0001

Data Index: 44023 (C4 (Web Text))

Max Activating Token Index: 999