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

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

Neuron 139 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: 0.2893. Min Range: -0.2893

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1280165 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2787. Min Act: -0.0001

Data Index: 634559 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1277301 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2770. Min Act: -0.0001

Data Index: 151709 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1023938 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1225001 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1085054 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2590. Min Act: -0.0001

Data Index: 584578 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2659. Min Act: -0.0001

Data Index: 953352 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2512. Min Act: -0.0001

Data Index: 721591 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2341. Min Act: -0.0001

Data Index: 604186 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1158103 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1165564 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2489. Min Act: -0.0001

Data Index: 103122 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2099. Min Act: -0.0001

Data Index: 839210 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1614. Min Act: -0.0001

Data Index: 621025 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1256. Min Act: -0.0001

Data Index: 116426 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1303. Min Act: -0.0001

Data Index: 564926 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1191. Min Act: -0.0001

Data Index: 713222 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1049458 (C4 (Web Text))

Max Activating Token Index: 974