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

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

Neuron 1711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8829. Min Act: -0.0001

Data Index: 73857 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.9560. Min Act: -0.0000

Data Index: 132975 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8505. Min Act: -0.0000

Data Index: 854527 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1043457 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8890. Min Act: -0.0000

Data Index: 202985 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8546. Min Act: -0.0000

Data Index: 913023 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.9525. Min Act: -0.0000

Data Index: 651264 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8547. Min Act: -0.0000

Data Index: 324321 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8328. Min Act: -0.0000

Data Index: 831154 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1091670 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8501. Min Act: -0.0001

Data Index: 268462 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.8357. Min Act: -0.0001

Data Index: 987961 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7912. Min Act: -0.0001

Data Index: 807460 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7618. Min Act: -0.0001

Data Index: 1167516 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7582. Min Act: -0.0000

Data Index: 42556 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7117. Min Act: -0.0001

Data Index: 1067140 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7789. Min Act: -0.0001

Data Index: 561432 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1015306 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1050005 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.9560. Min Range: -0.9560

Max Act: 0.7442. Min Act: -0.0001

Data Index: 849937 (C4 (Web Text))

Max Activating Token Index: 174