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

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

Neuron 3769 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0003

Data Index: 712748 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1128484 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0408. Min Act: -0.0003

Data Index: 200668 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1178074 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0362. Min Act: -0.0002

Data Index: 677782 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1278580 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1191015 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1126353 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1656921 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0350. Min Act: -0.0003

Data Index: 476842 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0349. Min Act: -0.0003

Data Index: 741001 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0348. Min Act: -0.0003

Data Index: 588913 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0340. Min Act: -0.0003

Data Index: 370720 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1554983 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0350. Min Act: -0.0003

Data Index: 148882 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0340. Min Act: -0.0003

Data Index: 478604 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1487413 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1057459 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1279635 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0328. Min Act: -0.0003

Data Index: 937832 (C4 (Web Text))

Max Activating Token Index: 215