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

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

Neuron 1547 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.4603. Min Act: -0.0000

Data Index: 995014 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.2905. Min Act: -0.0000

Data Index: 758073 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.1045. Min Act: -0.0000

Data Index: 1111230 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.0393. Min Act: -0.0000

Data Index: 880874 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.0446. Min Act: -0.0000

Data Index: 813673 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.0153. Min Act: -0.0000

Data Index: 350757 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.0086. Min Act: -0.0000

Data Index: 1071780 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.0946. Min Act: -0.0000

Data Index: 911145 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.8434. Min Act: -0.0000

Data Index: 305861 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 2.4603. Min Range: -2.4603

Max Act: 2.0621. Min Act: -0.0000

Data Index: 331986 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.9535. Min Act: -0.0000

Data Index: 443962 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.9134. Min Act: -0.0000

Data Index: 155253 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.8809. Min Act: -0.0000

Data Index: 14715 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.8455. Min Act: -0.0000

Data Index: 897915 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.9377. Min Act: -0.0000

Data Index: 906455 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.7964. Min Act: -0.0000

Data Index: 1608874 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1508932 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.7706. Min Act: -0.0000

Data Index: 44489 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.7670. Min Act: -0.0000

Data Index: 366444 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 2.4603. Min Range: -2.4603

Max Act: 1.8610. Min Act: -0.0000

Data Index: 903112 (C4 (Web Text))

Max Activating Token Index: 37