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

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

Neuron 3023 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3274. Min Act: -0.0001

Data Index: 41160 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3172. Min Act: -0.0001

Data Index: 973118 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3166. Min Act: 0.0000

Data Index: 230184 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2941. Min Act: 0.0000

Data Index: 900365 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1176319 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.3019. Min Act: 0.0000

Data Index: 319667 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2869. Min Act: -0.0001

Data Index: 553920 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2929. Min Act: -0.0000

Data Index: 517272 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2967. Min Act: -0.0000

Data Index: 729506 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2865. Min Act: -0.0000

Data Index: 421241 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2859. Min Act: -0.0001

Data Index: 70359 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1252873 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2711. Min Act: -0.0001

Data Index: 328821 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2701. Min Act: -0.0000

Data Index: 843774 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1082959 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1074612 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1205754 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1124046 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2724. Min Act: -0.0000

Data Index: 506377 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.3274. Min Range: -0.3274

Max Act: 0.2711. Min Act: -0.0000

Data Index: 210838 (C4 (Web Text))

Max Activating Token Index: 740