Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5180. Min Range: -1.5180

Max Act: 1.5180. Min Act: -0.0000

Data Index: 533739 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.5180. Min Range: -1.5180

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1113785 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.5180. Min Range: -1.5180

Max Act: 1.1183. Min Act: -0.0000

Data Index: 2321 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.9828. Min Act: -0.0000

Data Index: 801524 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.9043. Min Act: -0.0000

Data Index: 664696 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1195649 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1016327 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1103144 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8222. Min Act: -0.0000

Data Index: 597052 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.7668. Min Act: -0.0000

Data Index: 907396 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8901. Min Act: -0.0001

Data Index: 512313 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.7525. Min Act: -0.0000

Data Index: 889366 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.7848. Min Act: -0.0000

Data Index: 435920 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.7719. Min Act: -0.0000

Data Index: 632324 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1218427 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8107. Min Act: -0.0000

Data Index: 595384 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1283698 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1205661 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.8036. Min Act: -0.0001

Data Index: 844785 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.5180. Min Range: -1.5180

Max Act: 0.6674. Min Act: -0.0000

Data Index: 953381 (C4 (Web Text))

Max Activating Token Index: 775