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

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

Neuron 1287 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: 0.3119. Min Range: -0.3119

Max Act: 0.3119. Min Act: -0.0001

Data Index: 473757 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.3005. Min Act: -0.0000

Data Index: 656712 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2996. Min Act: 0.0000

Data Index: 554095 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.3071. Min Act: -0.0001

Data Index: 597187 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2957. Min Act: -0.0000

Data Index: 633776 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2875. Min Act: -0.0001

Data Index: 872002 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2946. Min Act: -0.0001

Data Index: 576209 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2728. Min Act: -0.0000

Data Index: 363238 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2846. Min Act: -0.0000

Data Index: 636291 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1026809 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2583. Min Act: -0.0001

Data Index: 375432 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2591. Min Act: -0.0000

Data Index: 779755 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2644. Min Act: -0.0001

Data Index: 771439 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1349601 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2639. Min Act: -0.0001

Data Index: 1329087 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2546. Min Act: 0.0001

Data Index: 1258177 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2590. Min Act: -0.0001

Data Index: 423740 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2720. Min Act: -0.0001

Data Index: 946278 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2602. Min Act: 0.0002

Data Index: 908141 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2589. Min Act: -0.0001

Data Index: 960314 (C4 (Web Text))

Max Activating Token Index: 624