Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2382 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1115285 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.4236. Min Act: -0.0000

Data Index: 224702 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1071255 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1286560 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3758. Min Act: -0.0000

Data Index: 728209 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3509. Min Act: -0.0000

Data Index: 517420 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3778. Min Act: -0.0000

Data Index: 980432 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3558. Min Act: -0.0000

Data Index: 231735 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3315. Min Act: -0.0000

Data Index: 791784 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3460. Min Act: -0.0000

Data Index: 991893 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3621. Min Act: -0.0000

Data Index: 981479 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1312225 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3354. Min Act: -0.0000

Data Index: 564491 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3508. Min Act: -0.0000

Data Index: 484939 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3178. Min Act: -0.0000

Data Index: 333133 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3020. Min Act: -0.0000

Data Index: 629641 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3238. Min Act: -0.0000

Data Index: 712917 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1204678 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3083. Min Act: -0.0000

Data Index: 217971 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1295326 (C4 (Web Text))

Max Activating Token Index: 449