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

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

Neuron 2672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2746. Min Act: -0.0001

Data Index: 97059 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2259. Min Act: -0.0001

Data Index: 550793 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2394. Min Act: -0.0001

Data Index: 8784 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1402. Min Act: -0.0001

Data Index: 39362 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1541. Min Act: -0.0001

Data Index: 248678 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1484. Min Act: -0.0001

Data Index: 1031287 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0944. Min Act: -0.0001

Data Index: 356629 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1187. Min Act: -0.0001

Data Index: 377889 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1499. Min Act: -0.0001

Data Index: 958655 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1168. Min Act: -0.0001

Data Index: 831722 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0950. Min Act: -0.0001

Data Index: 271990 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1069985 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0442. Min Act: -0.0000

Data Index: 226116 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0376. Min Act: -0.0001

Data Index: 916030 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0741. Min Act: -0.0001

Data Index: 309158 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0907. Min Act: -0.0001

Data Index: 109150 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0887. Min Act: -0.0001

Data Index: 364468 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0913. Min Act: -0.0001

Data Index: 1155464 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0227. Min Act: -0.0001

Data Index: 999305 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0896. Min Act: -0.0001

Data Index: 29235 (C4 (Web Text))

Max Activating Token Index: 652