Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 373 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1149248 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0531. Min Act: -0.0004

Data Index: 32059 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0526. Min Act: -0.0003

Data Index: 971194 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1162154 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0499. Min Act: -0.0003

Data Index: 844881 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0499. Min Act: -0.0004

Data Index: 958296 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0492. Min Act: -0.0003

Data Index: 762733 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0468. Min Act: -0.0003

Data Index: 345769 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0498. Min Act: -0.0003

Data Index: 895154 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0483. Min Act: -0.0003

Data Index: 846253 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0478. Min Act: -0.0003

Data Index: 291415 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0476. Min Act: -0.0003

Data Index: 519817 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0481. Min Act: -0.0002

Data Index: 643569 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0473. Min Act: -0.0003

Data Index: 562274 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0467. Min Act: -0.0003

Data Index: 122208 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0492. Min Act: -0.0003

Data Index: 948198 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1188119 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0474. Min Act: -0.0004

Data Index: 162340 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0476. Min Act: -0.0003

Data Index: 352198 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1155703 (C4 (Web Text))

Max Activating Token Index: 18