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

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

Neuron 270 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: 0.4042. Min Range: -0.4042

Max Act: 0.4042. Min Act: -0.0001

Data Index: 131696 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3594. Min Act: -0.0001

Data Index: 847317 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3531. Min Act: -0.0001

Data Index: 935687 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3455. Min Act: -0.0001

Data Index: 1356394 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3456. Min Act: -0.0001

Data Index: 620071 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3010. Min Act: -0.0001

Data Index: 884834 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3282. Min Act: -0.0000

Data Index: 731733 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2588. Min Act: -0.0001

Data Index: 240300 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3507. Min Act: -0.0001

Data Index: 211410 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2714. Min Act: -0.0001

Data Index: 406555 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2700. Min Act: -0.0001

Data Index: 930451 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2892. Min Act: -0.0001

Data Index: 816285 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2732. Min Act: -0.0001

Data Index: 742139 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2862. Min Act: -0.0001

Data Index: 988562 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2724. Min Act: -0.0000

Data Index: 309528 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2581. Min Act: -0.0001

Data Index: 82831 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1028608 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1223800 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2322. Min Act: -0.0001

Data Index: 370826 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1476704 (Python Code)

Max Activating Token Index: 256