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

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

Neuron 3689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0683. Min Act: -0.0001

Data Index: 652024 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1175349 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0625. Min Act: -0.0001

Data Index: 29974 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0561. Min Act: -0.0001

Data Index: 422689 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0598. Min Act: -0.0001

Data Index: 74786 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0466. Min Act: -0.0001

Data Index: 336453 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0506. Min Act: -0.0001

Data Index: 337312 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1356046 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1013236 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1096665 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1187698 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0487. Min Act: -0.0001

Data Index: 582687 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0463. Min Act: -0.0001

Data Index: 614357 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0401. Min Act: -0.0001

Data Index: 200952 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0434. Min Act: -0.0001

Data Index: 405586 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0444. Min Act: -0.0001

Data Index: 979155 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0451. Min Act: -0.0001

Data Index: 277731 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1086475 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0408. Min Act: -0.0001

Data Index: 598384 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0418. Min Act: -0.0001

Data Index: 130219 (C4 (Web Text))

Max Activating Token Index: 571